NAMIC Wiki - User contributions [en]

2016 Summer Project Week/CameraTutorial

2016-06-02T13:19:12Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Santhirarajah Mathimugan
* Steve Pieper

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* a tutorial that explains: a) how to connect a [http://www.baslerweb.com/en/products/cameras/area-scan-cameras/dart dart USB camera] from Basler to a PC b) grab the images and c) write a simple program in C++ for simple object detection.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
*
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2016 Summer Project Week/CameraTutorial

2016-06-02T13:16:50Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Santhirarajah Mathimugan
* Steve Pieper

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* a tutorial that explains, how to connect a dart USB camera from Basler to a PC, grab the image and write a simple program for object detection.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
*
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2016 Summer Project Week/CameraTutorial

2016-06-02T13:16:16Z

PeterBehringer:

__NOTOC__
<gallery>
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Santhirarajah Mathimugan
* Steve Pieper

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* a tutorial, how to connect a dart USB camera from Basler to a PC, grab the image and write a simple program for object detection.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
*
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2016 Summer Project Week/CameraTutorial

2016-06-02T13:14:20Z

PeterBehringer: Created page with "__NOTOC__ <gallery> Image:PW-Summer2016.png|Projects List </gallery> ==Key Investigators== * Peter Behringer * ==Project Description==..."

__NOTOC__
<gallery>
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
*

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
*
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
*
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2016 Summer Project Week

2016-06-02T13:13:21Z

PeterBehringer:

__NOTOC__

[[image:PW-Summer2016.png|300px]]
<br><br>
=Welcome to the web page for the 23rd Project Week!=
The 23rd Project Week open source hackathon is being held in conjunction with the [http://www.cars-int.org/ 30th International Conference on Computer Assisted Radiology and Surgery] (CARS) and the [http://www.ipcai.org/ IPCAI 2016] conferences in Heidelberg, Germany. Please go through this page for information, and if you have questions, please contact [https://www.spl.harvard.edu/pages/People/tkapur Tina Kapur, PhD].

='''Logistics'''=
*'''Dates:''' Monday June 20th to Saturday June 25th, 2016, with one day break on Tuesday June 21st to attend IPCAI.
*'''Location:''' Heidelberg, Germany.
**'''Monday''' at German Cancer Research Center - DKFZ
**'''Tuesday''' there is '''no''' organized Project Week activity due to IPCAI @ CARS
**'''Wednesday-Saturday''' at the Congress Hall of CARS.
*'''REGISTRATION:''' Please register for the CARS conference at http://www.cars-int.org/cars_2016/registration.html
*'''Registration Fee:''' Euro 650 (after April 26, 2016)
*'''Hotel:''' After registration, you can book hotels using the CARS organization at http://germany.nethotels.com/info/heidelberg/events/cars/default_en.htm or on your own. Please remember that Project Week starts on Monday June 20th, even though the formal CARS/IPCAI program starts a day later, so you will need to pay attention while booking the hotel room.
*Preparatory Conference Calls:
**800-501-8979. The pin is 7327389. ([http://www.windstreambusiness.com/resources/user-guides/international-conferencing International dialing instructions are available here])
**Call #1 Tuesday, May 10, 3pm Boston time.
**Call #2 Tuesday, May 17, 3pm Boston time.
**Call #3 Tuesday, May 31, 9am Boston time.
**Call #4 Tuesday, Jun 7, 9am Boston time.
**Call #5 Tuesday, Jun 14, 9am Boston time.

='''Agenda'''=
<font color="maroon">Please note that on '''Tuesday''' there is no organized Project Week activity due to IPCAI @ CARS</font>
{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:7%" |Time
!style="width:15%" |Monday, June 20 <br> DKFZ
!style="width:3%" |Tuesday, June 21 <br> IPCAI
!style="width:15%" |Wednesday, June 22 <br> Congress Hall of CARS
!style="width:15%" |Thursday, June 23 <br> Congress Hall of CARS
!style="width:15%" |Friday, June 24 <br> Congress Hall of CARS
!style="width:15%" |Saturday, June 25 <br> Congress Hall of CARS
|-
|bgcolor="#ffffdd"|'''9:00am-12:00pm'''
|bgcolor="#ffffff"| DKFZ Discussions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|[[Breakout Session: Shared Software Platform for Ultrasound-Guided Medical Interventions]]
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"| Progress Review
|-
|bgcolor="#ffffdd"|'''12:00pm-1:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffff"|
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch and adjourn
|-
|bgcolor="#ffffdd"|'''1:00pm-3:00pm'''
|bgcolor="#ffffff"| Welcome! <br> Project Introductions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffff"| 3:30pm: Breakout Session: Slicer Extensions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|-
|bgcolor="#ffffdd"|'''6:00pm'''
|bgcolor="#f0e68b"|
|bgcolor="#ffffff"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|-
|}

='''Background'''=
Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws researchers from around the world. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

The 23rd Project Week is being held in conjunction with the [http://www.ipcai.org/ IPCAI 2016] conference that is hosted by the [http://www.cars-int.org/ 30th International Conference on Computer Assisted Radiology and Surgery] (CARS).

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list].

='''Equipment'''=
*[[2016_Summer_Project_Week:Equipment|Specialized equipment people are going to bring]] (Please add to this list if you are bringing anything)
*[[2016_Summer_Project_Week:Equipment_Requests|Specialized equipment that people would like to have]]

='''Projects'''=
* Use this [[2016_Summer_Project_Week_Template | template]] for project pages

=== IGT ===
* [[2016 Summer Project Week/OpenIGTLink Robotics | Integrating/Using OpenIGTLink for the communications of Robotics devices]] (Scheherazade Kraß, Longquan Chen)
* [[2016 Summer Project Week/Needle Segmentation from MRI | Needle Segmentation from MRI]] (Tina Kapur, Andre Mastmeyer, Guillaume Pernelle)
* [[2016 Summer Project Week/Guided Ultrasound Calibration | Guided Ultrasound Calibration]] (Elvis Chen, Inês Prata, Tamas Ungi)
* [[2016 Summer Project Week/Tracked Ultrasound Standardization | Tracked Ultrasound Standardization II: The Implementering]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Longquan Chen, Adam Rankin, Thomas Kirchner, Janne Beate Bakeng)
* [[2016 Summer Project Week/Integrating PLUS in applications using OpenIGTLink | Integrating PLUS in applications using OpenIGTLink]] (Christian Askeland, Janne Beate Bakeng, Ole Vegard Solberg, Jon Eiesland, Longquan Chen, Simon Drouin)
* [[2016 Summer Project Week/SliceTracker | SliceTracker for data collection and prostate biopsy support ]] (Christian Herz, Peter Behringer, Andrey Fedorov)
* [[2016 Summer Project Week/Sacral Neuromodulation | Sacral Neuromodulation ]] (Javier Pascau, Rocío López, Tamas Ungi)

=== Infrastructure ===
* [[2016 Summer Project Week/3D Lasso Selection | Implementation, and testing performance, of 3-D Lasso selection within the segmentation editor infrastructure ]] (Davide Punzo, Csaba Pinter, Andras Lasso, Steve Pieper?)
* [[2016 Summer Project Week/Segmentations Integration | Integration of Segmentations infrastructure and related modules to Slicer core]] (Csaba Pinter, Andras Lasso)
* [[2016 Summer Project Week/DICOM Tractography Results | Finalizing DICOM Tractography Results implementation in DCMTK for BWH project]] (Michael Onken)

=== Augmented Reality ===
* [[2016 Summer Project Week/VRPN Integration | VRPN Integration]] (Dženan Zukić)
* [[2016 Summer Project Week/OpenVR_integration | OpenVR Integration]] (Adam Rankin)
* [[2016 Summer Project Week/AR with a tablet device in the surgical room | AR with a tablet device in the surgical room]] (Javier Pascau, David García)

=== Cloud ===
* [[2016 Summer Project Week/medical imaging webapp | Medical Imaging WebApp Software]] (Steve Pieper, Marco Nolden, Hans Meine)

=== Informatics ===
* [[2016 Summer Project Week/DICOM Parametric Maps | Finalizing DICOM Parametric Map implementation in DCMTK for QIICR project]] (Michael Onken, Jan Schlamelcher)
* [[2016 Summer Project Week/dcmqi | DICOM for Quantitative Imaging (dcmqi) library]] (Andrey Fedorov, Christian Herz, Marco Nolden, Hans Meine, Csaba Pinter, Steve Pieper, et al)
* [[2016 Summer Project Week/MeVisLab SEG Colors | Support Reading and Writing DICOM Tags for SEG Colors]] (Hans Meine)
* [[2016 Summer Project Week/Segmentation Editor and Terminology | Segmentation Editor and Terminology]] (Nicole Aucoin, Andrey Fedorov, Csaba Pinter)

=== Tutorial===
* [[2016 Summer Project Week/CameraTutorial | How to use Basler cameras for medical applications]] (Peter Behringer, Santhirarajah Mathimugan, Steve Pieper?)

= '''Registrants''' =

'''REGISTRATION:''' Please add your name to this list if you are definitely planning to attend. If you are not already on it, please add yourself to the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]. We need to know the number of people at DKFZ, so if you are there on Monday, please add "(Mon)" next to your name. Official registration for the event is through the CARS conference at http://www.cars-int.org/cars_2016/registration.html -- which you can do now or onsite.

#Tina Kapur, Brigham and Women's Hospital, Harvard Medical School (BWH/HMS), Boston, USA (Mon)
# Dženan Zukić, Kitware, USA
# Ines Prata Machado, MIT Portugal Program (PhD Student), Lisbon, Portugal. (Mon)
# Sonia Pujol, Brigham and Women's Hospital, Harvard Medical School (Mon)
# Scheherazade Kraß, PhD Student, [http://www.uni-bremen.de/ University of Bremen], [http://www.mic.uni-bremen.de/ Medical Image Computing]group, Germany (Mon)
# Maria Francesca Spadea [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Paolo Zaffino [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Salvatore Scaramuzzino [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Steve Pieper, Isomics, Inc., USA (Mon)
# Nicole Aucoin, Brigham and Women's Hospital (Mon)
# Simon Drouin, Montreal Neurological Institute (Mon)
# Thomas Kirchner, German Cancer Research Center (Mon)
# Elvis Chen, [http://www.imaging.robarts.ca/petergrp/Research Robarts Research Institute], Canada (Mon)
# Adam Rankin, [http://www.imaging.robarts.ca/petergrp/Research Robarts Research Institute], Canada (Mon)
# Christian Askeland, SINTEF, Norway (Mon)
# Hans Meine, University of Bremen / Fraunhofer MEVIS, Germany
# Longquan Chen, BWH/HMS, Boston, USA (Mon)
# Davide Punzo, Kapteyn Astronomical Institute, Netherlands (Mon)
# Lauren O'Donnell, BWH/HMS
# Yannick Suter, BWH/HMS
# Junichi Tokuda, BWH/HMS (Mon)
# Sarah Frisken, BWH/HMS (Mon)
# Prashin Unadkat, BWH/HMS
# Anna Roethe, Charite, Berlin
# Michael Onken, Open Connections, Germany
#Jan Schlamelcher, Open Connections/OFFIS, Germany
# Janne Beate Bakeng, SINTEF, Norway
# Ole Vegard Solberg, SINTEF, Norway
# Jon Eiesland, SINTEF, Norway
# Tamas Ungi, Queen's University, Canada (Mon)
# Andras Lasso, Queen's University, Canada (Mon)
# Csaba Pinter, Queen's University, Canada (Mon)
# Thomas Vaughan, Queen's University, Canada (Mon)
#Gabor Fichtinger, Queen's University, Canada
# Javier Pascau, Universidad Carlos III de Madrid, Spain (Mon)
# Verónica García-Vazquez, Universidad Carlos III de Madrid, Spain (Mon)
# Mónica García-Sevilla, Universidad Carlos III de Madrid, Spain (Mon)
# David García-Mato, Universidad Carlos III de Madrid, Spain (Mon)
# Rocío López-Velazco, Universidad Carlos III de Madrid, Spain (Mon)
# Raúl San José, BWH/HMS, Boston
# Pietro Nardeli, BWH/HMS, Boston
# Andrey Fedorov, BWH/HMS, Boston (Mon)
# Christian Herz, BWH/HMS, Boston (Mon)
# Frank Lindseth, NTNU/SINTEF, Norway
# Peter Behringer, Basler AG, Germany
# Santhirarajah Mathimugan, Basler AG, Germany

2016 Summer Project Week

2016-06-02T12:04:09Z

PeterBehringer: /* Registrants */

__NOTOC__

[[image:PW-Summer2016.png|300px]]
<br><br>
=Welcome to the web page for the 23rd Project Week!=
The 23rd Project Week open source hackathon is being held in conjunction with the [http://www.cars-int.org/ 30th International Conference on Computer Assisted Radiology and Surgery] (CARS) and the [http://www.ipcai.org/ IPCAI 2016] conferences in Heidelberg, Germany. Please go through this page for information, and if you have questions, please contact [https://www.spl.harvard.edu/pages/People/tkapur Tina Kapur, PhD].

='''Logistics'''=
*'''Dates:''' Monday June 20th to Saturday June 25th, 2016, with one day break on Tuesday June 21st to attend IPCAI.
*'''Location:''' Heidelberg, Germany.
**'''Monday''' at German Cancer Research Center - DKFZ
**'''Tuesday''' there is '''no''' organized Project Week activity due to IPCAI @ CARS
**'''Wednesday-Saturday''' at the Congress Hall of CARS.
*'''REGISTRATION:''' Please register for the CARS conference at http://www.cars-int.org/cars_2016/registration.html
*'''Registration Fee:''' Euro 650 (after April 26, 2016)
*'''Hotel:''' After registration, you can book hotels using the CARS organization at http://germany.nethotels.com/info/heidelberg/events/cars/default_en.htm or on your own. Please remember that Project Week starts on Monday June 20th, even though the formal CARS/IPCAI program starts a day later, so you will need to pay attention while booking the hotel room.
*Preparatory Conference Calls:
**800-501-8979. The pin is 7327389. ([http://www.windstreambusiness.com/resources/user-guides/international-conferencing International dialing instructions are available here])
**Call #1 Tuesday, May 10, 3pm Boston time.
**Call #2 Tuesday, May 17, 3pm Boston time.
**Call #3 Tuesday, May 31, 9am Boston time.
**Call #4 Tuesday, Jun 7, 9am Boston time.
**Call #5 Tuesday, Jun 14, 9am Boston time.

='''Agenda'''=
<font color="maroon">Please note that on '''Tuesday''' there is no organized Project Week activity due to IPCAI @ CARS</font>
{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:7%" |Time
!style="width:15%" |Monday, June 20 <br> DKFZ
!style="width:3%" |Tuesday, June 21 <br> IPCAI
!style="width:15%" |Wednesday, June 22 <br> Congress Hall of CARS
!style="width:15%" |Thursday, June 23 <br> Congress Hall of CARS
!style="width:15%" |Friday, June 24 <br> Congress Hall of CARS
!style="width:15%" |Saturday, June 25 <br> Congress Hall of CARS
|-
|bgcolor="#ffffdd"|'''9:00am-12:00pm'''
|bgcolor="#ffffff"| DKFZ Discussions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|[[Breakout Session: Shared Software Platform for Ultrasound-Guided Medical Interventions]]
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"| Progress Review
|-
|bgcolor="#ffffdd"|'''12:00pm-1:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffff"|
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch and adjourn
|-
|bgcolor="#ffffdd"|'''1:00pm-3:00pm'''
|bgcolor="#ffffff"| Welcome! <br> Project Introductions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffff"| 3:30pm: Breakout Session: Slicer Extensions
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|bgcolor="#ffffff"|
|-
|bgcolor="#ffffdd"|'''6:00pm'''
|bgcolor="#f0e68b"|
|bgcolor="#ffffff"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|
|-
|}

='''Background'''=
Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws researchers from around the world. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

The 23rd Project Week is being held in conjunction with the [http://www.ipcai.org/ IPCAI 2016] conference that is hosted by the [http://www.cars-int.org/ 30th International Conference on Computer Assisted Radiology and Surgery] (CARS).

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list].

='''Equipment'''=
*[[2016_Summer_Project_Week:Equipment|Specialized equipment people are going to bring]] (Please add to this list if you are bringing anything)
*[[2016_Summer_Project_Week:Equipment_Requests|Specialized equipment that people would like to have]]

='''Projects'''=
* Use this [[2016_Summer_Project_Week_Template | template]] for project pages

=== IGT ===
* [[2016 Summer Project Week/OpenIGTLink Robotics | Integrating/Using OpenIGTLink for the communications of Robotics devices]] (Scheherazade Kraß, Longquan Chen)
* [[2016 Summer Project Week/Needle Segmentation from MRI | Needle Segmentation from MRI]] (Tina Kapur, Andre Mastmeyer, Guillaume Pernelle)
* [[2016 Summer Project Week/Guided Ultrasound Calibration | Guided Ultrasound Calibration]] (Elvis Chen, Inês Prata, Tamas Ungi)
* [[2016 Summer Project Week/Tracked Ultrasound Standardization | Tracked Ultrasound Standardization II: The Implementering]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Longquan Chen, Adam Rankin, Thomas Kirchner, Janne Beate Bakeng)
* [[2016 Summer Project Week/Integrating PLUS in applications using OpenIGTLink | Integrating PLUS in applications using OpenIGTLink]] (Christian Askeland, Janne Beate Bakeng, Ole Vegard Solberg, Jon Eiesland, Longquan Chen, Simon Drouin)
* [[2016 Summer Project Week/SliceTracker | SliceTracker for data collection and prostate biopsy support ]] (Christian Herz, Peter Behringer, Andrey Fedorov)
* [[2016 Summer Project Week/Sacral Neuromodulation | Sacral Neuromodulation ]] (Javier Pascau, Rocío López, Tamas Ungi)

=== Infrastructure ===
* [[2016 Summer Project Week/3D Lasso Selection | Implementation, and testing performance, of 3-D Lasso selection within the segmentation editor infrastructure ]] (Davide Punzo, Csaba Pinter, Andras Lasso, Steve Pieper?)
* [[2016 Summer Project Week/Segmentations Integration | Integration of Segmentations infrastructure and related modules to Slicer core]] (Csaba Pinter, Andras Lasso)
* [[2016 Summer Project Week/DICOM Tractography Results | Finalizing DICOM Tractography Results implementation in DCMTK for BWH project]] (Michael Onken)

=== Augmented Reality ===
* [[2016 Summer Project Week/VRPN Integration | VRPN Integration]] (Dženan Zukić)
* [[2016 Summer Project Week/OpenVR_integration | OpenVR Integration]] (Adam Rankin)
* [[2016 Summer Project Week/AR with a tablet device in the surgical room | AR with a tablet device in the surgical room]] (Javier Pascau, David García)

=== Cloud ===
* [[2016 Summer Project Week/medical imaging webapp | Medical Imaging WebApp Software]] (Steve Pieper, Marco Nolden, Hans Meine)

=== Informatics ===
* [[2016 Summer Project Week/DICOM Parametric Maps | Finalizing DICOM Parametric Map implementation in DCMTK for QIICR project]] (Michael Onken, Jan Schlamelcher)
* [[2016 Summer Project Week/dcmqi | DICOM for Quantitative Imaging (dcmqi) library]] (Andrey Fedorov, Christian Herz, Marco Nolden, Hans Meine, Csaba Pinter, Steve Pieper, et al)
* [[2016 Summer Project Week/MeVisLab SEG Colors | Support Reading and Writing DICOM Tags for SEG Colors]] (Hans Meine)
* [[2016 Summer Project Week/Segmentation Editor and Terminology | Segmentation Editor and Terminology]] (Nicole Aucoin, Andrey Fedorov, Csaba Pinter)

= '''Registrants''' =

'''REGISTRATION:''' Please add your name to this list if you are definitely planning to attend. If you are not already on it, please add yourself to the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]. We need to know the number of people at DKFZ, so if you are there on Monday, please add "(Mon)" next to your name. Official registration for the event is through the CARS conference at http://www.cars-int.org/cars_2016/registration.html -- which you can do now or onsite.

#Tina Kapur, Brigham and Women's Hospital, Harvard Medical School (BWH/HMS), Boston, USA (Mon)
# Dženan Zukić, Kitware, USA
# Ines Prata Machado, MIT Portugal Program (PhD Student), Lisbon, Portugal. (Mon)
# Sonia Pujol, Brigham and Women's Hospital, Harvard Medical School (Mon)
# Scheherazade Kraß, PhD Student, [http://www.uni-bremen.de/ University of Bremen], [http://www.mic.uni-bremen.de/ Medical Image Computing]group, Germany (Mon)
# Maria Francesca Spadea [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Paolo Zaffino [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Salvatore Scaramuzzino [http://www.imagenglab.com ImagEngLab], Italy (Mon)
# Steve Pieper, Isomics, Inc., USA (Mon)
# Nicole Aucoin, Brigham and Women's Hospital (Mon)
# Simon Drouin, Montreal Neurological Institute (Mon)
# Thomas Kirchner, German Cancer Research Center (Mon)
# Elvis Chen, [http://www.imaging.robarts.ca/petergrp/Research Robarts Research Institute], Canada (Mon)
# Adam Rankin, [http://www.imaging.robarts.ca/petergrp/Research Robarts Research Institute], Canada (Mon)
# Christian Askeland, SINTEF, Norway (Mon)
# Hans Meine, University of Bremen / Fraunhofer MEVIS, Germany
# Longquan Chen, BWH/HMS, Boston, USA (Mon)
# Davide Punzo, Kapteyn Astronomical Institute, Netherlands (Mon)
# Lauren O'Donnell, BWH/HMS
# Yannick Suter, BWH/HMS
# Junichi Tokuda, BWH/HMS (Mon)
# Sarah Frisken, BWH/HMS (Mon)
# Prashin Unadkat, BWH/HMS
# Anna Roethe, Charite, Berlin
# Michael Onken, Open Connections, Germany
#Jan Schlamelcher, Open Connections/OFFIS, Germany
# Janne Beate Bakeng, SINTEF, Norway
# Ole Vegard Solberg, SINTEF, Norway
# Jon Eiesland, SINTEF, Norway
# Tamas Ungi, Queen's University, Canada (Mon)
# Andras Lasso, Queen's University, Canada (Mon)
# Csaba Pinter, Queen's University, Canada (Mon)
# Thomas Vaughan, Queen's University, Canada (Mon)
#Gabor Fichtinger, Queen's University, Canada
# Javier Pascau, Universidad Carlos III de Madrid, Spain (Mon)
# Verónica García-Vazquez, Universidad Carlos III de Madrid, Spain (Mon)
# Mónica García-Sevilla, Universidad Carlos III de Madrid, Spain (Mon)
# David García-Mato, Universidad Carlos III de Madrid, Spain (Mon)
# Rocío López-Velazco, Universidad Carlos III de Madrid, Spain (Mon)
# Raúl San José, BWH/HMS, Boston
# Pietro Nardeli, BWH/HMS, Boston
# Andrey Fedorov, BWH/HMS, Boston (Mon)
# Christian Herz, BWH/HMS, Boston (Mon)
# Frank Lindseth, NTNU/SINTEF, Norway
# Peter Behringer, Basler AG, Germany
# Santhirarajah Mathimugan, Basler AG, Germany

2015 Refinement Registration Module

2015-06-24T14:59:06Z

PeterBehringer: /* Project Description */

__NOTOC__
{|
| Case 25
|[[Image:RegResults.png |thumb|600px|Enabled switching through registration results]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Module for registration of the prostate was developed in Slicer 4. See code [https://github.com/PeterBehringer/Registration here]
* Our objective is to make the module more generic, so that in can also be used by clinical staff during more procedures that require preop/intraop or intraop/intraop registration
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
* Presented the module to several expert clinicians
* Got valuable feedback on how to improve usability and code
</div>
</div>

2015 Refinement Registration Module

2015-06-24T14:57:27Z

PeterBehringer:

2015 Refinement Registration Module

2015-06-24T14:57:13Z

PeterBehringer:

__NOTOC__
{|
| Case 25
|[[Image:RegResults.png |thumb|400px|Enabled switching through registration results]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Module for registration of the prostate was developed in Slicer 4. See code [https://github.com/PeterBehringer/Registration here]
* Our objective is to make the module more generic, so that in can also be used by clinical staff during more procedures that require preop/intraop or intraop/intraop registration
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
</div>
</div>

File:RegResults.png

2015-06-24T14:56:26Z

PeterBehringer:

File:Screen 2015-06-24 um 16.22.55.png

2015-06-24T14:55:12Z

PeterBehringer:

2015 BRAINSFit registration in SimpleITK

2015-06-24T14:48:34Z

PeterBehringer: /* Project Description */

__NOTOC__

{|
| Case 25
|[[Image:HighIrregulation.gif‎ |thumb|400px|High irregulations in ITKv4]]
|[[Image:fixedIrregulations.gif|thumb|400px|Resolved Irregulations ins ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov
* Dženan Zukić

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here])
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
* We tracked the issue down using various parameters
* We used strongly dilated masks for the BSpline registration and results are looking much better
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-24T14:46:52Z

PeterBehringer:

2015 BRAINSFit registration in SimpleITK

2015-06-24T14:46:37Z

PeterBehringer:

__NOTOC__

{|
| Case 25
|[[Image:HighIrregulation.gif‎ |thumb|300px|High irregulations in ITKv4]]
|[[Image:fixedIrregulations.gif|thumb|300px|Resolved Irregulations ins ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov
* Dženan Zukić

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here])
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

File:FixedIrregulations.gif

2015-06-24T14:45:48Z

PeterBehringer:

File:HighIrregulation.gif

2015-06-24T14:45:07Z

PeterBehringer:

File:OutputEhSITV.gif

2015-06-24T14:44:01Z

PeterBehringer:

File:Output EhSITV.gif

2015-06-24T14:41:59Z

PeterBehringer:

2015 BRAINSFit registration in SimpleITK

2015-06-10T15:11:14Z

PeterBehringer: /* Key Investigators */

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov
* Dženan Zukić

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here])
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 Summer Project Week

2015-06-10T15:10:58Z

PeterBehringer:

__NOTOC__

[[image:PW-Summer2015.png|300px]]
<br>

'''Welcome to the web page for the 21st Project Week! This is the first Project Week that is being held in conjunction with the [http://www.cars-int.org/ CARS conference].'''

==Logistics==

*'''Dates:''' June 21-24, 2015.
*'''Location:''' [http://www.nh-collection.com/hotel/nh-collection-barcelona-constanza NH Collection Constanza Hotel, Barcelona, Spain]
*'''REGISTRATION:''' Please register by adding your name to the list at the end of this page
*'''Registration Fee:''' None. The organizers will cover the charge for the conference room, while all attendees are responsible for their own hotel rooms as well as food.
*'''Hotel:''' You are welcome to book a room using the CARS 2015 conference services ([http://www.cars-int.org/fileadmin/templates/download/2015/CARS_2015_accomondation.pdf Click here for form])
*To attend the CARS meeting, please visit [http://www.cars-int.org/ http://www.cars-int.org/]

==Agenda==

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Sunday, June 21
!style="width:18%" |Monday, June 22
!style="width:18%" |Tuesday, June 23
!style="width:18%" |Wednesday, June 24
|-
|bgcolor="#ffffdd"|'''10:00am-3:00pm:'''
|rowspan=3 valign=bottom|<hr>'''6pm''' Meeting with All Participants in Hotel Constanza Lobby
|'''10:00-11am:''' <font color="#503020">Rapid Introduction of all Projects and Teams <br>
'''11am-3pm''' <font color="#503020">Work <br>

|
'''10:00am-11am:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014_Project_Week_Breakout_Session: Slicer for users| Slicer for users]] (Ron Kikinis) <br>
'''11am-3pm''' <font color="#503020">Work
|'''10am-3pm''' <font color="#503020">Work <br>
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|-
|bgcolor="#ffffdd"|'''5:00-7:00pm'''
|'''5:00-7pm:''' <font color="#503020"> Work
|'''5:00-7:00pm:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2015_Summer_Project_Week/SoftwareStack| Open Software Stack]] (Steve Pieper)
|'''5:00-6pm:''' <font color="#503020"> Work <br>
'''6:00-7pm:''' Report Progress
|-
|bgcolor="#ffffdd"|'''7:00pm'''
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|}

== '''Background''' ==

Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws researchers from around the world. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

The 21st Project Week is being held on conjunction with the [http://www.cars-int.org/ CARS conference].

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]

=Projects=
* [[2015_Summer_Project_Week_Template | Template for project pages]]

==Equipment==

==Image-Guided Therapy==
*[[2015 Orthognathic Surgery|Orthognathic Surgery]] (Dženan Zukić, Kitware)
*[http://www.na-mic.org/Wiki/index.php/2015_pyDBS pyDBS module update to Slicer4.4 (Sara Fernandez-Vidal, Yulong Zhao, Sonia Pujol)]
*[[2015_pilot trajectory planning | Pilot Trajectory Planning(Caroline Essert, Sonia Pujol)]]
*[http://www.na-mic.org/Wiki/index.php/2015_Multi_atlas_based_prostate_segmentation Multi atlas based prostate segmentation] (Paolo Zaffino, Giampaolo Pileggi, Salvatore Scaramuzzino, Peter Behringer, Andrey Fedorov, Maria Francesca Spadea)
*[[2015_Summer_Project_Week:SlicerIGT|SlicerIGT tutorials for use cases]] (Tamas Ungi)
*[http://www.na-mic.org/Wiki/index.php/2015_Refinement_Registration_Module Refinement of RegistrationModule] (Peter Behringer, Andrey Fedorov)
*[http://www.na-mic.org/Wiki/index.php/2015_BRAINSFit_registration_in_SimpleITK BRAINSFit registration in SimpleITK] (Peter Behringer, Andrey Fedorov, Dženan Zukić)
*[http://www.na-mic.org/Wiki/index.php/2015_Multimodal_Guidance_for_Breast_Cancer_Surgery Multimodal Guidance for Breast Cancer Surgery] (Mikael Brudfors, Javier Pascau)
*[[2015_Summer_Project_Week:LinearFeatureRegistration|Linear Feature Registration]] (Matthew Holden)

==Feature Based Image Analysis==
*[[2015_Summer_Project_Week:LungCAD| LungCAD]] (Jayender Jagadeesan, Tobias Penzkofer, Sandy Wells)
*[[2015_Summer_Project_Week:QuantitativeProstate | Texture Analysis for Prostate Imaging]] (Tobias Penzkofer, Jay Jagadeesan, Tina Kapur)
*[[2015_Summer_Project_Week:BigDataFeatures | Big Data Medical Image Analysis using Local Features]] (Matthew Toews, William Wells, Tina Kapur)
*[[2015_Summer_Project_Week:USReconstruction | Gated 3D Ultrasound Reconstructions with the Help of a Single-Element US Transducer ]] (Frank Preiswerk, Laurent Chauvin)
*[[2015_Summer_Project_Week:AutomaticCephalometric | Automatic Cephalometric Analysis ]] (J. Jesus Montufar, Marcelo Romero)
*[[2015_Summer_Project_Week:LightWeightRobotIGT | Integration of a KUKA robot using OpenIGTLink ]] (Sebastian Tauscher, Junichi Tokuda)

==Astronomy==
*[[2015_Summer_Project_Week:Astronomy | visualization of HI in galaxies]] (Davide Punzo)

==Infrastructure==
*[[2015_Summer_Project_Week:DCMTK| Integration and testing of new DCMTK with Slicer]] (Michael Onken, Andrey Fedorov)
*[[2015_Summer_Project_Week:Python_scripts_from_command_line|Simplify use of python scripts from the command line]] (Andrey Fedorov, Steve Pieper, Robin Weiss, Artem Mamonov)
*[[2015_Summer_Project_Week:CLIModules_Backgrounding_in_MeVisLab | Running CLI Modules in the background in MeVisLab]] (Hans Meine)
*[[2015_Summer_Project_Week:CLIModules_Indexing | CLI Modules elasticsearch / kibana dashboard]] (Hans Meine, JC, Steve Pieper)
*[[2015_Summer_Project_Week:CTK_Interative_Plugins | CTK plugins / paths towards interoperability with GUI & interaction]] (Hans Meine, ??)
*[[2015_Summer_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with "interesting" CLI modules (BRAINSFit, CIP, UKFTractography?) in MeVisLab (/Frontier)]] (Hans Meine, Steve Pieper)
*[[2015_Summer_Project_Week:Return_Fiducials_from_CLIs | Return fiducials from CLIs]] (Nicole Aucoin, Jim Miller)
*[[2015_Summer_Project_Week:Update Checker | Update Checker]] (Franklin King, BWH)
*[[2015_Summer_Project_Week:Integrated Virtual Reality Viewer | Integrated Virtual Reality Viewer]] (Franklin King, BWH)
*[[2015_Summer_Project_Week:SegmentationNode| Use new Segmentation node in Editor]] (Andras Lasso, Steve Pieper)
*[[2015_Summer_Project_Week:IGTSliceletBase| Create base classes for IGT slicelet]] (Andras Lasso, Andrey Fedorov)

==Web / DCMJS==
*[[2015_Summer_Project_Week:Dicom parsing with DCMJS | Dicom parsing with DCMJS]] (Nicolas Rannou, Steve Pieper)
*[[2015_Summer_Project_Week:Volume rendering with DCMJS and THREEJS | Volume Rendering with DCMJS and THREEJS]] (Nicolas Rannou, Steve Pieper)

==QIICR==
*[[2015_Summer_Project_Week:DSC | Dynamic Susceptibility Contrast MRI (DSC) for brain ]] (Xiao Da)
*[[2015_Summer_Project_Week:T1 mapping | T1 mapping for DCE ]] (Xiao Da)

== '''Registrants''' ==

Please add your name to the list. This is the registration mechanism for this project week.
#Tina Kapur, BWH
#Ron Kikinis, BWH & Fraunhofer
#Steve Pieper, Isomics
#Tamas Ungi, Queen's University, Canada
#Andras Lasso, Queen's University, Canada
#Paolo Zaffino, ImagEngLab, Magna Graecia University, Italy
#Salvatore Scaramuzzino, ImagEngLab, Magna Graecia University, Italy
#Giampaolo Pileggi, ImagEngLab, Magna Graecia University, Italy
#Hans Meine, Fraunhofer MEVIS, Bremen, Germany
#Nicole Aucoin, BWH
#Sonia Pujol, BWH
#Dženan Zukić, Kitware, Carrboro, NC
#Jayender Jagadeesan, BWH
#Guido Gerig, Utah
#Sandy Wells, BWH
#Matthew Toews, École de Technologie Supérieure, Montreal, Canada
#Frank Preiswerk, BWH
#Junichi Tokuda, BWH
#Raul San Jose, BWH
#Jorge Onieva, BWH
#Yulong Zhao, Université de Rennes
#Laurent Chauvin, BWH
#Michael Onken, Open Connections
#Tobias Penzkofer, Department of Radiology, Charité Berlin, Germany
#Javier Pascau, Universidad Carlos III de Madrid, Spain
#Angel Torrado-Carvajal, Universidad Rey Juan Carlos, Madrid, Spain
#Nobuhiko Hata, BWH
#Robert H. Owen, BK Medical ApS, Denmark
#Clare Tempany, BWH
#Adam Rankin, Robarts
#Utsav Pardasani, Robarts
#Marcelo Romero, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#J. Jesus Montufar, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#Davide Punzo, Kapteyn Astronomical Institute, University of Groningen, Netherlands
#Andrey Fedorov, BWH
#Nicolas Rannou, BCH
#Mikael Brudfors, Universidad Carlos III de Madrid, Spain
#Laura Sanz, Universidad Carlos III de Madrid, Spain
#Eugenio Marinetto, Universidad Carlos III de Madrid, Spain
#David García, Universidad Carlos III de Madrid, Spain
#Franklin King, Queen's University / BWH
#Jorge García, Universidad Politécnica de Madrid, Spain
#Peter Behringer, BWH
#Caroline Essert, University of Strasbourg
#Pradyumna Reddy, Birla Institute of Technology and Science, Goa-Campus, India.
#Sebastian Tauscher, Institute of Mechatronic Systems, Leibniz Universität Hannover, Germany
#Matthew Holden, Queen's University, Canada

2015 BRAINSFit registration in SimpleITK

2015-06-07T02:47:34Z

PeterBehringer: /* Project Description */

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here])
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T21:58:34Z

PeterBehringer: /* Project Description */

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T21:58:13Z

PeterBehringer: /* Project Description */

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with Slicer4/ITKv4 is that there are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T21:57:51Z

PeterBehringer: /* Project Description */

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with ITKv4 is that there are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T21:56:51Z

PeterBehringer:

__NOTOC__
{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with ITKv4 is that there are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]
*

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T21:55:47Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with ITKv4 is that there are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]
*

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 Refinement Registration Module

2015-06-04T21:15:10Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Module for registration of the prostate was developed in Slicer 4. See code [https://github.com/PeterBehringer/Registration here]
* Our objective is to make the module more generic, so that in can also be used by clinical staff during more procedures that require preop/intraop or intraop/intraop registration
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T18:47:22Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with ITKv4 is that are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]
*

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Implement BRAINSFit functionality in SimpleITK
* Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration is implemented using SimpleITK
</div>
</div>

2015 BRAINSFit registration in SimpleITK

2015-06-04T18:45:08Z

PeterBehringer: Created page with '__NOTOC__ <gallery> Image:PW-Summer2015.png|Projects List </gallery> ==Key Investigators== * Peter Behringer * Andriy Fedorov ==Project De…'

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
* One issue that we are getting with ITKv4 is that are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here]
*

</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Initialization and rigid registration phase is functional
</div>
</div>

2015 Summer Project Week

2015-06-04T18:28:46Z

PeterBehringer: /* Image-Guided Therapy */

__NOTOC__

[[image:PW-Summer2015.png|300px]]
<br>

'''Welcome to the web page for the 21st Project Week! This is the first Project Week that is being held in conjunction with the [http://www.cars-int.org/ CARS conference].'''

==Logistics==

*'''Dates:''' June 21-24, 2015.
*'''Location:''' [http://www.nh-collection.com/hotel/nh-collection-barcelona-constanza NH Collection Constanza Hotel, Barcelona, Spain]
*'''REGISTRATION:''' Please register by adding your name to the list at the end of this page
*'''Registration Fee:''' None. The organizers will cover the charge for the conference room, while all attendees are responsible for their own hotel rooms as well as food.
*'''Hotel:''' You are welcome to book a room using the CARS 2015 conference services ([http://www.cars-int.org/fileadmin/templates/download/2015/CARS_2015_accomondation.pdf Click here for form])
*To attend the CARS meeting, please visit [http://www.cars-int.org/ http://www.cars-int.org/]

==Agenda==

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Sunday, June 21
!style="width:18%" |Monday, June 22
!style="width:18%" |Tuesday, June 23
!style="width:18%" |Wednesday, June 24
|-
|bgcolor="#ffffdd"|'''10:00am-3:00pm:'''
|rowspan=3 valign=bottom|<hr>'''6pm''' Meeting with All Participants
|'''10:00-11am:''' <font color="#503020">Rapid Introduction of all Projects and Teams <br>
'''11am-3pm''' <font color="#503020">Work <br>

|
'''10:00am-11am:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014_Project_Week_Breakout_Session: Slicer for users| Slicer for users]] (Ron Kikinis) <br>
'''11am-3pm''' <font color="#503020">Work
|'''10am-3pm''' <font color="#503020">Work <br>
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|-
|bgcolor="#ffffdd"|'''5:00-7:00pm'''
|'''5:00-7pm:''' <font color="#503020"> Work
|'''5:00-7:00pm:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2015_Summer_Project_Week/SoftwareStack| Open Software Stack]] (Steve Pieper)
|'''5:00-6pm:''' <font color="#503020"> Work <br>
'''6:00-7pm:''' Report Progress
|-
|bgcolor="#ffffdd"|'''7:00pm'''
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|}

== '''Background''' ==

Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws 80-120 researchers. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

The 21st Project Week is being held on conjunction with the [http://www.cars-int.org/ CARS conference].

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]

=Projects=
* [[2015_Summer_Project_Week_Template | Template for project pages]]

==Image-Guided Therapy==
*[[2015 Orthognatic Surgery|Orthognatic Surgery]] (Dženan Zukić, Kitware)
*[http://www.na-mic.org/Wiki/index.php/2015_pyDBS pyDBS module update to Slicer4.4 (Sara Fernandez-Vidal, Yulong Zhao, Sonia Pujol)]
*[http://www.na-mic.org/Wiki/index.php/2015_Multi_atlas_based_prostate_segmentation Multi atlas based prostate segmentation] (Paolo Zaffino, Giampaolo Pileggi, Salvatore Scaramuzzino, Peter Behringer, Andrey Fedorov, Maria Francesca Spadea)
*[[2015_Summer_Project_Week:SlicerIGT|SlicerIGT tutorials for use cases]] (Tamas Ungi)
*[http://www.na-mic.org/Wiki/index.php/2015_Refinement_Registration_Module Refinement of RegistrationModule] (Peter Behringer, Andrey Fedorov)
*[http://www.na-mic.org/Wiki/index.php/2015_BRAINSFit_registration_in_SimpleITK BRAINSFit registration in SimpleITK] (Peter Behringer, Andrey Fedorov)

==Feature Based Image Analysis==
*[[2015_Summer_Project_Week:LungCAD| LungCAD]] (Jayender Jagadeesan)
*[[2015_Summer_Project_Week:QuantitativeProstate | Texture Analysis for Prostate Imaging]] (Tobias Penzkofer, Jay Jagadeesan, Tina Kapur)
*[[2015_Summer_Project_Week:BigDataFeatures | Big Data Medical Image Analysis using Local Features]] (Matthew Toews, William Wells, Tina Kapur)

==Astronomy==
*[[2015_Summer_Project_Week:Astronomy | visualization of HI in galaxies]] (Davide Punzo)

==Infrastructure==
*[[2015_Summer_Project_Week:DCMTK| Integration and testing of new DCMTK with Slicer]] (Michael Onken, Andrey Fedorov)
*[[2015_Summer_Project_Week:Python_scripts_from_command_line|Simplify use of python scripts from the command line]] (Andrey Fedorov, Steve Pieper, Robin Weiss, Artem Mamonov)
*[[2015_Summer_Project_Week:CLIModules_Backgrounding_in_MeVisLab | Running CLI Modules in the background in MeVisLab]] (Hans Meine)
*[[2015_Summer_Project_Week:CLIModules_Indexing | CLI Modules elasticsearch / kibana dashboard]] (Hans Meine, JC)
*[[2015_Summer_Project_Week:CTK_Interative_Plugins | CTK plugins / paths towards interoperability with GUI & interaction]] (Hans Meine, ??)
*[[2015_Summer_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with "interesting" CLI modules (BRAINSFit, CIP, UKFTractography?) in MeVisLab (/Frontier)]] (Hans Meine, Steve Pieper)
*[[2015_Summer_Project_Week:Return_Fiducials_from_CLIs | Return fiducials from CLIs]] (Nicole Aucoin, Jim Miller)
*[[2015_Summer_Project_Week:Update Checker | Update Checker]] (Frankling King, BWH)
*[[2015_Summer_Project_Week:Integrated Virtual Reality Viewer | Integrated Virtual Reality Viewer]] (Frankling King, BWH)

==Web / DCMTKJS==
*[[2015_Summer_Project_Week:Porting Slicer to the web | Porting Slicer to the web]] (Nicolas Rannou)

== '''Registrants''' ==

Please add your name to the list. This is the registration mechanism for this project week.
#Tina Kapur, BWH
#Ron Kikinis, BWH & Fraunhofer
#Steve Pieper, Isomics
#Tamas Ungi, Queen's University, Canada
#Andras Lasso, Queen's University, Canada
#Paolo Zaffino, ImagEngLab, Magna Graecia University, Italy
#Salvatore Scaramuzzino, ImagEngLab, Magna Graecia University, Italy
#Giampaolo Pileggi, ImagEngLab, Magna Graecia University, Italy
#Hans Meine, Fraunhofer MEVIS, Bremen, Germany
#Nicole Aucoin, BWH
#Sonia Pujol, BWH
#Dženan Zukić, Kitware, Carrboro, NC
#Jayender Jagadeesan, BWH
#Guido Gerig, Utah
#Sandy Wells, BWH
#Matthew Toews, École de Technologie Supérieure, Montreal, Canada
#Frank Preiswerk, BWH
#Junichi Tokuda, BWH
#Raul San Jose, BWH
#Jorge Onieva, BWH
#James Ross, BWH
#Yulong Zhao, Université de Rennes
#Laurent Chauvin, BWH
#Michael Onken, Open Connections
#Tobias Penzkofer, Department of Radiology, Charité Berlin, Germany
#Javier Pascau, Universidad Carlos III de Madrid, Spain
#Angel Torrado-Carvajal, Universidad Rey Juan Carlos, Madrid, Spain
#Nobuhiko Hata, BWH
#Robert H. Owen, BK Medical ApS, Denmark
#Clare Tempany, BWH
#Adam Rankin, Robarts
#Utsav Pardasani, Robarts
#Marcelo Romero, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#J. Jesus Montufar, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#Davide Punzo, Kapteyn Astronomical Institute, University of Groningen, Netherlands
#Andrey Fedorov, BWH
#Nicolas Rannou, BCH
#Mikael Brudfors, Universidad Carlos III de Madrid, Spain
#Laura Sanz, Universidad Carlos III de Madrid, Spain
#Eugenio Marinetto, Universidad Carlos III de Madrid, Spain
#David García, Universidad Carlos III de Madrid, Spain
#Franklin King, Queen's University / BWH
#Jorge García, Universidad Politécnica de Madrid, Spain
#Peter Behringer, BWH
#Caroline Essert, University of Strasbourg

2015 Refinement Registration Module

2015-06-04T18:25:16Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Module for registration of the prostate was developed in Slicer 4. See code [https://github.com/PeterBehringer/Registration here]
* Our objective is to make the module more generic, so that in can also be used by clinical staff for other procedures that require registration
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
</div>
</div>

2015 Refinement Registration Module

2015-06-04T18:22:06Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* 3D Slicer 4 module for intra-procedural registration of the prostate was developed. See code [https://github.com/PeterBehringer/Registration here]
* To make the module more generic (not only prostate biopsies), we want to get feedback from the community about potential features that are not implemented yet
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Get feedback about the workflow and usability
* Identify potential additional use cases and functionalities that make the module more generic
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
</div>
</div>

2015 Refinement Registration Module

2015-06-04T18:20:45Z

PeterBehringer: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Summer2015.png|[[2015_Summer_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
* Peter Behringer
* Andriy Fedorov

==Project Description==
<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* 3D Slicer 4 module for intra-procedural registration of the prostate was developed. See code [https://github.com/PeterBehringer/Registration here]
* To make the module more generic (not only prostate biopsies), we want to get feedback from the community about potential features that are not implemented yet
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* Present the module to interested members of the community
* Identify potential use cases and functionalities
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* The module is functional
</div>
</div>

2015 Refinement Registration Module

2015-06-04T18:17:14Z

PeterBehringer: /* Project Description */

2015 Refinement Registration Module

2015-06-04T18:11:53Z

PeterBehringer: Created page with '__NOTOC__ <gallery> Image:PW-Summer2015.png|Projects List </gallery> ==Key Investigators== * Peter Behringer * Andriy Fedorov ==Project De…'

2015 Summer Project Week

2015-06-04T18:10:03Z

PeterBehringer: /* Image-Guided Therapy */

__NOTOC__

[[image:PW-Summer2015.png|300px]]
<br>

'''Welcome to the web page for the 21st Project Week! This is the first Project Week that is being held in conjunction with the [http://www.cars-int.org/ CARS conference].'''

==Logistics==

*'''Dates:''' June 21-24, 2015.
*'''Location:''' [http://www.nh-collection.com/hotel/nh-collection-barcelona-constanza NH Collection Constanza Hotel, Barcelona, Spain]
*'''REGISTRATION:''' Please register by adding your name to the list at the end of this page
*'''Registration Fee:''' None. The organizers will cover the charge for the conference room, while all attendees are responsible for their own hotel rooms as well as food.
*'''Hotel:''' You are welcome to book a room using the CARS 2015 conference services ([http://www.cars-int.org/fileadmin/templates/download/2015/CARS_2015_accomondation.pdf Click here for form])
*To attend the CARS meeting, please visit [http://www.cars-int.org/ http://www.cars-int.org/]

==Agenda==

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Sunday, June 21
!style="width:18%" |Monday, June 22
!style="width:18%" |Tuesday, June 23
!style="width:18%" |Wednesday, June 24
|-
|bgcolor="#ffffdd"|'''10:00am-3:00pm:'''
|rowspan=3 valign=bottom|<hr>'''6pm''' Meeting with All Participants
|'''10:00-11am:''' <font color="#503020">Rapid Introduction of all Projects and Teams <br>
'''11am-3pm''' <font color="#503020">Work <br>

|
'''10:00am-11am:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014_Project_Week_Breakout_Session: Slicer for users| Slicer for users]] (Ron Kikinis) <br>
'''11am-3pm''' <font color="#503020">Work
|'''10am-3pm''' <font color="#503020">Work <br>
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|-
|bgcolor="#ffffdd"|'''5:00-7:00pm'''
|'''5:00-7pm:''' <font color="#503020"> Work
|'''5:00-7:00pm:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2015_Summer_Project_Week/SoftwareStack| Open Software Stack]] (Steve Pieper)
|'''5:00-6pm:''' <font color="#503020"> Work <br>
'''6:00-7pm:''' Report Progress
|-
|bgcolor="#ffffdd"|'''7:00pm'''
|bgcolor="#f0e68b"|
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|}

== '''Background''' ==

Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws 80-120 researchers. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

The 21st Project Week is being held on conjunction with the [http://www.cars-int.org/ CARS conference].

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]

=Projects=
* [[2015_Summer_Project_Week_Template | Template for project pages]]

==Image-Guided Therapy==
*[[2015 Orthognatic Surgery|Orthognatic Surgery]] (Dženan Zukić, Kitware)
*[http://www.na-mic.org/Wiki/index.php/2015_pyDBS pyDBS module update to Slicer4.4 (Sara Fernandez-Vidal, Yulong Zhao, Sonia Pujol)]
*[http://www.na-mic.org/Wiki/index.php/2015_Multi_atlas_based_prostate_segmentation Multi atlas based prostate segmentation] (Paolo Zaffino, Giampaolo Pileggi, Salvatore Scaramuzzino, Peter Behringer, Andrey Fedorov, Maria Francesca Spadea)
*[[2015_Summer_Project_Week:SlicerIGT|SlicerIGT tutorials for use cases]] (Tamas Ungi)
*[http://www.na-mic.org/Wiki/index.php/2015_Refinement_Registration_Module Refinement of RegistrationModule] (Peter Behringer, Andrey Fedorov)

==Feature Based Image Analysis==
*[[2015_Summer_Project_Week:LungCAD| LungCAD]] (Jayender Jagadeesan)
*[[2015_Summer_Project_Week:QuantitativeProstate | Texture Analysis for Prostate Imaging]] (Tobias Penzkofer, Jay Jagadeesan, Tina Kapur)
*[[2015_Summer_Project_Week:BigDataFeatures | Big Data Medical Image Analysis using Local Features]] (Matthew Toews, William Wells, Tina Kapur)

==Astronomy==
*[[2015_Summer_Project_Week:Astronomy | visualization of HI in galaxies]] (Davide Punzo)

==Infrastructure==
*[[2015_Summer_Project_Week:DCMTK| Integration and testing of new DCMTK with Slicer]] (Michael Onken, Andrey Fedorov)
*[[2015_Summer_Project_Week:Python_scripts_from_command_line|Simplify use of python scripts from the command line]] (Andrey Fedorov, Steve Pieper, Robin Weiss, Artem Mamonov)
*[[2015_Summer_Project_Week:CLIModules_Backgrounding_in_MeVisLab | Running CLI Modules in the background in MeVisLab]] (Hans Meine)
*[[2015_Summer_Project_Week:CLIModules_Indexing | CLI Modules elasticsearch / kibana dashboard]] (Hans Meine, JC)
*[[2015_Summer_Project_Week:CTK_Interative_Plugins | CTK plugins / paths towards interoperability with GUI & interaction]] (Hans Meine, ??)
*[[2015_Summer_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with "interesting" CLI modules (BRAINSFit, CIP, UKFTractography?) in MeVisLab (/Frontier)]] (Hans Meine, Steve Pieper)
*[[2015_Summer_Project_Week:Return_Fiducials_from_CLIs | Return fiducials from CLIs]] (Nicole Aucoin, Jim Miller)
*[[2015_Summer_Project_Week:Update Checker | Update Checker]] (Frankling King, BWH)
*[[2015_Summer_Project_Week:Integrated Virtual Reality Viewer | Integrated Virtual Reality Viewer]] (Frankling King, BWH)

==Web / DCMTKJS==
*[[2015_Summer_Project_Week:Porting Slicer to the web | Porting Slicer to the web]] (Nicolas Rannou)

== '''Registrants''' ==

Please add your name to the list. This is the registration mechanism for this project week.
#Tina Kapur, BWH
#Ron Kikinis, BWH & Fraunhofer
#Steve Pieper, Isomics
#Tamas Ungi, Queen's University, Canada
#Andras Lasso, Queen's University, Canada
#Paolo Zaffino, ImagEngLab, Magna Graecia University, Italy
#Salvatore Scaramuzzino, ImagEngLab, Magna Graecia University, Italy
#Giampaolo Pileggi, ImagEngLab, Magna Graecia University, Italy
#Hans Meine, Fraunhofer MEVIS, Bremen, Germany
#Nicole Aucoin, BWH
#Sonia Pujol, BWH
#Dženan Zukić, Kitware, Carrboro, NC
#Jayender Jagadeesan, BWH
#Guido Gerig, Utah
#Sandy Wells, BWH
#Matthew Toews, École de Technologie Supérieure, Montreal, Canada
#Frank Preiswerk, BWH
#Junichi Tokuda, BWH
#Raul San Jose, BWH
#Jorge Onieva, BWH
#James Ross, BWH
#Yulong Zhao, Université de Rennes
#Laurent Chauvin, BWH
#Michael Onken, Open Connections
#Tobias Penzkofer, Department of Radiology, Charité Berlin, Germany
#Javier Pascau, Universidad Carlos III de Madrid, Spain
#Angel Torrado-Carvajal, Universidad Rey Juan Carlos, Madrid, Spain
#Nobuhiko Hata, BWH
#Robert H. Owen, BK Medical ApS, Denmark
#Clare Tempany, BWH
#Adam Rankin, Robarts
#Utsav Pardasani, Robarts
#Marcelo Romero, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#J. Jesus Montufar, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#Davide Punzo, Kapteyn Astronomical Institute, University of Groningen, Netherlands
#Andrey Fedorov, BWH
#Nicolas Rannou, BCH
#Mikael Brudfors, Universidad Carlos III de Madrid, Spain
#Laura Sanz, Universidad Carlos III de Madrid, Spain
#Eugenio Marinetto, Universidad Carlos III de Madrid, Spain
#David García, Universidad Carlos III de Madrid, Spain
#Franklin King, Queen's University / BWH
#Jorge García, Universidad Politécnica de Madrid, Spain
#Peter Behringer, BWH
#Caroline Essert, University of Strasbourg

2015 Summer Project Week

2015-06-03T20:07:11Z

PeterBehringer: /* Registrants */

__NOTOC__

[[image:PW-Summer2015.png|300px]]
<br>

==Logistics==

Location: [http://www.nh-collection.com/hotel/nh-collection-barcelona-constanza NH COLLECTION CONSTANZA Hotel, Barcelona]

Agenda:

*Sunday, June 21st
** early evening: project presentations
* Monday June 22
* Tuesday June 23
** Late afternoon: breakout session on [[2015_Summer_Project_Week/SoftwareStack|the Open Software Stack]]
* Wednesday June 24
** Adjourn at 5pm

Registration Fee: zero. We will cover the charge for the conference room, while all attendees are responsible for their own hotel rooms as well as food.

==Agenda==

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Sunday, June 21
!style="width:18%" |Monday, June 22
!style="width:18%" |Tuesday, June 23
!style="width:18%" |Wednesday, June 24
|-
|bgcolor="#ffffdd"|'''7:00am-3:00pm:'''
|rowspan=3 valign=bottom|<hr>'''6:00-7:00pm''' Meeting with All Participants
|'''10:00-11:30am:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014 Project Week Breakout Session: DICOM|DICOM]] (Steve Pieper)
|
'''11:00am-12noon:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014_Project_Week_Breakout_Session: Slicer for users| Slicer for users]] (Ron Kikinis)
|'''10:00am-12noon:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014 Project Week Breakout Session: IGT Neuro|Image-Guided Therapy - Neurosurgery]] (Alexandra Golby, Tina Kapur) <br>
|-
|bgcolor="#ffffdd"|'''3:00pm-5:00pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|-
|bgcolor="#ffffdd"|'''5:00-7:00pm'''
|'''5:00-6:30pm:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2014 Project Week Breakout Session: Contours|Contours]] (Adam Rankin, Csaba Pinter)
|'''5:00-7:00pm:''' <font color="#503020">'''Breakout Session:'''</font><br>[[2015_Summer_Project_Week/SoftwareStack| Open Software Stack]] (Steve Pieper)
|
|-
|bgcolor="#ffffdd"|'''7:00pm'''
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|}

== '''Background''' ==

Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws 80-120 researchers. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event.

Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.

Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO], and [https://www.ncigt.org/IGTWiki/index.php/Projects/IGTWeb:R25 NCI Funded Image-Guided Fellowship Program].

A summary of all previous Project Events is available [[Project_Events#Past|here]].

This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.

Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]

=Projects=
* [[2015_Summer_Project_Week_Template | Template for project pages]]

==Image-Guided Therapy==
*[[2015 Orthognatic Surgery|Orthognatic Surgery]]

==Huntington's Disease==
==TBI==

==Stroke==

==Cardiac==

==Chronic Obstructive Pulmonary Disease, Lung, Chest ==
*[[2015_Summer_Project_Week:LungCAD| LungCAD]] (Jayender Jagadeesan)

==[http://qiicr.org QIICR]==
*[[2015_Summer_Project_Week:DCMTK| Integration and testing of new DCMTK with Slicer]] (Michael Onken, Andrey Fedorov)

==Quantitative Radiology==
*[[2015_Summer_Project_Week:QuantitativeProstate | Texture Analysis for Prostate Imaging]]

==Feature Extraction==
*[[2015_Summer_Project_Week:BigDataFeatures | Big Data Medical Image Analysis using Local Features]] (Matthew Toews, William Wells)

==Additional Brain Image Analysis==
*[http://www.na-mic.org/Wiki/index.php/2015_pyDBS pyDBS module update to Slicer4.4 (Sara Fernandez-Vidal, Yulong Zhao, Sonia Pujol)]

==Infrastructure==
*[[2015_Summer_Project_Week:Update Checker | Update Checker]]
*[[2015_Summer_Project_Week:Integrated Virtual Reality Viewer | Integrated Virtual Reality Viewer]]

==Astronomy==
*[[2015_Summer_Project_Week:Astronomy | visualization of HI in galaxies]] (Davide Punzo)

==Slicer4 Extensions==

==TMJOA RO1 - Collaboration with NAMIC==

==Infrastructure==
*[[2015_Summer_Project_Week:CLIModules_Backgrounding_in_MeVisLab | Running CLI Modules in the background in MeVisLab]] (Hans Meine)
*[[2015_Summer_Project_Week:CLIModules_Indexing | CLI Modules elasticsearch / kibana dashboard]] (Hans Meine, JC)
*[[2015_Summer_Project_Week:CTK_Interative_Plugins | CTK plugins / paths towards interoperability with GUI & interaction]] (Hans Meine, ??)
*[[2015_Summer_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with "interesting" CLI modules (BRAINSFit, CIP, UKFTractography?) in MeVisLab (/Frontier)]] (Hans Meine, Steve Pieper)
*[[2015_Summer_Project_Week:Return_Fiducials_from_CLIs | Return fiducials from CLIs]] (Nicole Aucoin, Jim Miller)
*[[2015_Summer_Project_Week:Python_scripts_from_command_line|Simplify use of python scripts from the command line]] (Andrey Fedorov, Steve Pieper, Robin Weiss, Artem Mamonov)

== '''Logistics''' ==

*'''Dates:''' June 21-24, 2015.
*'''Location:''' NH Collection Constanza Hotel, Barcelona, Spain
*'''REGISTRATION:''' Please register by adding your name to the list below
*'''Registration Fee:''' None
*'''Hotel:''' You are welcome to book a room using the CARS 2015 conference services ([http://www.cars-int.org/fileadmin/templates/download/2015/CARS_2015_accomondation.pdf Click here for form])
*'''Room sharing''': If interested, add your name to the list: [[2015_Summer_Project_Week/RoomSharing|here]]

== '''Registrants''' ==

Please add your name to the list. This is the registration mechanism for this project week.
#Tina Kapur, BWH
#Ron Kikinis, BWH & Fraunhofer
#Steve Pieper, Isomics
#Tamas Ungi, Queen's University, Canada
#Andras Lasso, Queen's University, Canada
#Paolo Zaffino, ImagEngLab, Magna Graecia University, Italy
#Salvatore Scaramuzzino, ImagEngLab, Magna Graecia University, Italy
#Giampaolo Pileggi, ImagEngLab, Magna Graecia University, Italy
#Hans Meine, Fraunhofer MEVIS, Bremen, Germany
#Nicole Aucoin, BWH
#Sonia Pujol, BWH
#Dženan Zukić, Kitware, Carrboro, NC
#Jayender Jagadeesan, BWH
#Guido Gerig, Utah
#Sandy Wells, BWH
#Matthew Toews, École de Technologie Supérieure, Montreal, Canada
#Frank Preiswerk, BWH
#Junichi Tokuda, BWH
#Jonathan Scalera, BWH
#Raul San Jose, BWH
#Jorge Onieva, BWH
#James Ross, BWH
#Yulong Zhao, Université de Rennes
#Laurent Chauvin, BWH
#Michael Onken, Open Connections
#Tobias Penzkofer, Department of Radiology, Charité Berlin, Germany
#Javier Pascau, Universidad Carlos III de Madrid, Spain
#Angel Torrado-Carvajal, Universidad Rey Juan Carlos, Madrid, Spain
#Nobuhiko Hata, BWH
#Robert H. Owen, BK Medical ApS, Denmark
#Clare Tempany, BWH
#Adam Rankin, Robarts
#Utsav Pardasani, Robarts
#Marcelo Romero, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#J. Jesus Montufar, Facultad de Ingenieria, Universidad Autonoma del Estado de Mexico, Mexico
#Davide Punzo, Kapteyn Astronomical Institute, University of Groningen, Netherlands
#Andrey Fedorov, BWH
#Nicolas Rannou, BCH
#Mikael Brudfors, Universidad Carlos III de Madrid, Spain
#Laura Sanz, Universidad Carlos III de Madrid, Spain
#Eugenio Marinetto, Universidad Carlos III de Madrid, Spain
#David García, Universidad Carlos III de Madrid, Spain
#Franklin King, Queen's University / BWH
#Jorge García, Universidad Politécnica de Madrid, Spain
#Peter Behringer, BWH

BRAINSFit prostate registration

2015-05-18T23:39:17Z

PeterBehringer: /* Current status */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 18, 2015'''

==Things to do==
* Set ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS to 1 as described [http://comments.gmane.org/gmane.comp.lib.itk.user/44256 here]
* Write message to ITK mailing list, cc Nicholas Tustin: ask for regularization of the BSpline displacement field
* look at DICE comparison between Slicer3 and Slicer4 to quantify the problem
* displace the masks and run with Slicer3 and Slicer4 to quantify the impact of the mask in the registration result

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-18T23:39:01Z

PeterBehringer: /* Things to do */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things to do==
* Set ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS to 1 as described [http://comments.gmane.org/gmane.comp.lib.itk.user/44256 here]
* Write message to ITK mailing list, cc Nicholas Tustin: ask for regularization of the BSpline displacement field
* look at DICE comparison between Slicer3 and Slicer4 to quantify the problem
* displace the masks and run with Slicer3 and Slicer4 to quantify the impact of the mask in the registration result

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-18T23:38:15Z

PeterBehringer: /* Things to do */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things to do==
* Set ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS to 1 as described here http://comments.gmane.org/gmane.comp.lib.itk.user/44256
* Write message to ITK mailing list, cc Nicholas Tustin: ask for regularization of the BSpline displacement field
* look at DICE comparison between Slicer3 and Slicer4 to quantify the problem
* displace the masks and run with Slicer3 and Slicer4 to quantify the impact of the mask in the registration result

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-18T14:56:58Z

PeterBehringer:

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things to do==
* Set Thread to 1 to in Slicer4
* Write message to ITK mailing list, cc Nicholas Tustin: ask for regularization of the BSpline displacement field
* look at DICE comparison between Slicer3 and Slicer4 to quantify the problem
* displace the masks and run with Slicer3 and Slicer4 to quantify the impact of the mask in the registration result

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-15T15:08:22Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-15T15:06:10Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI using [BRAINSFit https://github.com/BRAINSia/BRAINSTools/tree/master/BRAINSFit]
This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
** The ITKv4 ImageRegistrationMethod random sampling utilizes a fixed seed ([https://github.com/InsightSoftwareConsortium/ITK/blob/03f28bb2e0c4b3d00f1ceeb772b342746c89e148/Modules/Registration/RegistrationMethodsv4/include/itkImageRegistrationMethodv4.hxx#L903-L967 here])
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:30:53Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries and can be integrated in the latest Slicer versions.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:30:21Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here]) we are considering a C++ implementation that uses ITKv3 libraries but can be used in Slicer 4.4.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:30:09Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration#Standing_SimpleITK_issues here] we are considering a C++ implementation that uses ITKv3 libraries but can be used in Slicer 4.4.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:29:14Z

PeterBehringer: /* Goal */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see "Unresolved issues out of our direct control") we are considering a C++ implementation that uses ITKv3 libraries but can be used in Slicer 4.4.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:28:38Z

PeterBehringer: /* Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4 */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see "Unresolved issues out of our direct control") we are considering a C++ implementation that uses ITKv3 libraries.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:27:22Z

PeterBehringer: /* Results using the above parameters */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see "Unresolved issues out of our direct control") we are considering a C++ implementation that uses ITKv3 libraries.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option, instead: --samplingPercentage

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv3 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.

BRAINSFit prostate registration

2015-05-09T19:22:51Z

PeterBehringer: /* Results using the above parameters */

=Goal=

We are developing registration module in Slicer version 4 (which is using ITKv4) for deformable registration of prostate MRI.

We want to develop a prostate registration tool in Slicer4/ITKv4. This Slicer4/ITKv4 registration tool should be functional, accurate and fast (i.e., comparable with the functionality we had in Slicer3/ITKv3, which has been evaluated previously [1]). We worked on implementing BRAINSFit registration in SimpleITK but due to several issues (see "Unresolved issues out of our direct control") we are considering a C++ implementation that uses ITKv3 libraries.

=Details on the registration approach=
Registration is applied to align preprocedural and intraoperational MR T2 image volumes. We are using masks the prostate for both image data sets. Registration is done using MMI metric with rigid, affine and B-spline stages applied in sequence. In Slicer3/BRAINSFit we use gradient descent for rigid/affine, and LBFGS for B-spline.

=Parameters we are using to call BRAINSFit in Slicer 3.6 and Slicer 4.4=

{| class="wikitable"
|-
! Parameter !! Slicer 3.6 !! Slicer 4.4
|-
| --fixedVolume || dir || dir
|-
| --movingVolume || dir || dir
|-
| --outputVolume || dir || dir
|-
| --bsplineTransform || dir || dir
|-
| --movingBinaryVolume || dir || dir

|-
| --fixedBinaryVolume || dir || dir

|-
| --useCenterOfROIAlign || True || style="background:#cef2e0;"|   not an option

|-
| --initializeTransformMode || style="background:#cef2e0;"|   not an option || useCenterOfROIAlign

|-
| --samplingPercentage || style="background:#cef2e0;"|   not an option || 0.002

|-
| --useRigid || True || True

|-
| --useAffine || True || True

|-
| --useROIBSpline || True || True

|-
| --useScaleVersor3D || True || True

|-
| --useScaleSkewVersor3D || True || True

|-
| --useBSpline || style="background:#cef2e0;"|   not an option || True

|-
| --splineGridSize || 3,3,3 || 3,3,3

|-
| --numberOfIterations || 1500 || 1500

|-
| --maskProcessing || ROI || ROI

|-
| --outputVolumePixelType || float || float

|-
| --backgroundFillValue || 0 || 0

|-
| --maskInferiorCutOffFromCenter || 1000 || 1000

|-
| --interpolationMode || Linear || Linear

|-
| --minimumStepSize || 0.005 || style="background:#cef2e0;"|   not an option

|-
| --minimumStepLength || style="background:#cef2e0;"|   not an option || 0.005

|-
| --translationScale || 1000 || 1000

|-
| --reproportionScale || 1 || 1

|-
| --skewScale || 1 || 1

|-
| --numberOfHistogramBins || 50 || 50

|-
| --numberOfMatchPoints || 10 || 10

|-
| --numberOfSamples || 100000 || style="background:#cef2e0;"|   not an option, instead: --samplingPercentage

|-
| --fixedVolumeTimeIndex || 0 || 0

|-
| --movingVolumeTimeIndex || 0 || 0

|-
| --medianFilterSize || 0,0,0 || 0,0,0

|-
| --ROIAutoDilateSize || 0 || 0

|-
| --relaxationFactor || 0.5 || 0.5

|-
| --maximumStepSize || 0.2 || style="background:#cef2e0;"|   not an option

|-
| --maximumStepLength || style="background:#cef2e0;"|   not an option || 0.2

|-
| --failureExitCode || -1 || -1

|-
| --debugNumberOfThreads || -1 || style="background:#cef2e0;"|   not an option

|-
| --numberOfThreads || style="background:#cef2e0;"|   not an option || -1

|-
| --debugLevel || 0 || 0

|-
| --costFunctionConvergenceFactor || 1.00E+09 || 1.00E+09

|-
| --projectedGradientTolerance || 1.00E-05 || 1.00E-05

|-
| --maxBSplineDisplacement || 0 || 0

|-
| --maximumNumberOfEvaluations || style="background:#cef2e0;"|   not an option || 900

|-
| --maximumNumberOfCorrections || style="background:#cef2e0;"|   not an option || 25

|-
| --metricSamplingStrategy || style="background:#cef2e0;"|   not an option || Random

|-
| --costMetric || style="background:#cef2e0;"|   not an option || MMI

|-
| --removeIntensityOutliers || style="background:#cef2e0;"|   not an option || 0

|-
| --ROIAutoClosingSize || style="background:#cef2e0;"|   not an option || 9

|-
| --useExplicitPDFDerivativesMode || AUTO || style="background:#cef2e0;"|   not an option

|-
| --useCachingOfBSplineWeightsMode || ON || style="background:#cef2e0;"|   not an option

|}

=Results using the above parameters=
We used [http://www.slicer.org/publications/item/view/2147 this sample data] with Reader 1 segmentations to visually evaluate differences in the registration results.
All three results of BRAINSFit with ITKv4 in Slicer 3.6 look reasonable. Using BRAINSFit with ITKv4 in Slicer 4.4 creates a reasonable result for Case 7, but look strongly distorted towards the edges of the bounding box in Case 8 and 9.

{|
| Case 7
|[[Image:pat7-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat7-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat7-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 8
|[[Image:pat8-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat8-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat8-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

{|
| Case 9
|[[Image:pat9-ref.png‎ |thumb|300px|Reference intraop volume]]
|[[Image:pat9-3_6.png|thumb|300px|Reg Result Slicer 3.6 with ITKv3]]
|[[Image:pat9-4_4.png|thumb|300px|Reg Result Slicer 4.4 with ITKv4]]
|}

=Current status=

SimpleITK registration code on github: [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/BRAINSFit_to_sitk_MMI.py here]

'''Latest update: Mai 9, 2015'''

==Things that are working==
* exhaustive search based initialization procedure implemented and produces good results (cross-correlation metric) in SimpleITK

==Things that are implemented, but are not working==
* SimpleITK code for rigid registration
** the voxel sampling exception can be avoided by cropping the images sharply around the masks.
{|
|
|[[Image:FixedVolume.png|thumb|300px|Fixed Volume as Reference]]
|[[Image:AfterInit.png|thumb|300px|SimpleITK result after Initialization]]
|[[Image:AfterRigid.png|thumb|300px|SimpleITK result after rigid registration]]
|[[Image:BRAINSFitOut.png|thumb|300px|BRAINSFit result after rigid without using masks and --useCenterOfGeometryAlign]]
|}
** The rigid registration result is too much rotated and translated. Also the number of iteration steps varies with every computation. Reason might be that seed is set randomized and not set as done in BRAINSFit [https://github.com/BRAINSia/BRAINSTools/blob/af0ff12b8b751f9423061d42178268acab5f85f4/BRAINSCommonLib/BRAINSFitHelper.h#L375 here]. There is no option at the [http://www.itk.org/SimpleITKDoxygen/html/classitk_1_1simple_1_1ImageRegistrationMethod.html SimpleITK::ImageRegistrationMethod] to set a metric seed.

==Things that are not implemented, but need to be implemented==
* SimpleITK code for affine registration
** setting affineOptimizer [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L158-L187 here]
** setting RegistrationMethod [https://github.com/BRAINSia/BRAINSTools/blob/19fa37dfbdee37deff4ccee412bb601f7a787bda/BRAINSCommonLib/genericRegistrationHelper.hxx#L289-L353 here]
* SimpleITK code for BSpline registration (started [https://github.com/PeterBehringer/SimpleITKtraining/blob/master/simpleITK_to_sitk_BSpline.py here])

=Unresolved issues out of our direct control=
==Standing SimpleITK issues==
* no API for consistent initialization of the metric seed
*

==Standing ITKv4 issues==
* capability to sample voxels only within the mask (see topic under review on Gerrit: http://review.source.kitware.com/#/c/19684/)
*

==Standing Slicer4 issues==
=References=
[1] Fedorov A, Tuncali K, Fennessy FM, Tokuda J, Hata N, et al. (2012) Image registration for targeted MRI-guided transperineal prostate biopsy. J Magn Reson Imaging 36: 987–992. Available: http://dx.doi.org/10.1002/jmri.23688.