NAMIC Wiki - User contributions [en]

2017 Winter Project Week/Population Based Image Imputation

2017-01-13T14:36:57Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT, MGH
*Katie Bouman, MIT
*Mert Sabuncu, MGH, Cornell
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.
|

* Implemented entire algorithm on GPU.
* Comparing 4-CPU with a GTX1080, we gain significant speedup when dimensionality of subspace is large, but in the realistic scenario (subspace has low dimensionality) the speedup is only ~2x.
* Banding in images found to be due to bad cluster assignment of patches. We're working on assigning cluster assignment of patches based on original subject space rather than atlas space.
|}

==Background and References==

2017 Winter Project Week/Population Based Image Imputation

2017-01-09T18:41:32Z

Adalca: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT, MGH
*Katie Bouman, MIT
*Mert Sabuncu, MGH, Cornell
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.
|


|}

==Background and References==

2017 Winter Project Week

2017-01-09T18:19:33Z

Adalca:

__NOTOC__
[[image:PW-Winter2017.png|300px]]

=Welcome to the web page for the 24th Project Week!=

The 24th NA-MIC Project Week open source hackathon is being held during the week of January 9-13, 2017 at MIT. 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:''' January 9-13, 2017.
*'''Location:''' [https://www.google.com/maps/place/MIT:+Computer+Science+and+Artificial+Intelligence+Laboratory/@42.361864,-71.090563,16z/data=!4m2!3m1!1s0x0:0x303ada1e9664dfed?hl=en MIT CSAIL], Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)
*'''Transportation:''' Public transportation is highly encouraged, as no parking permits will be issued by MIT. For a list of local garages, please see [http://web.mit.edu/facilities/transportation/parking/visitors/public_parking.html here]
*'''REGISTRATION:''' Register [https://www.regonline.com/2017projectweek here]. Registration Fee: $330.
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.
*'''Next Project Week:'''' [http://wiki.na-mic.org/Wiki/index.php/2017_Summer_Project_Week June 26-30, 2017, Catanzaro, Italy]

== Introduction ==
The National Alliance for Medical Image Computing (NAMIC), was founded in 2005 and 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], enhancements to the underlying building blocks [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 open source hackathon event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual open source hackathon which draws 60-120 researchers. As of August 2014, it is a [http://www.miccai.org/organization 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], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO].

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

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

==Conference Calls for Preparation==

Conference call phone number and notes are available [[TCONS:2017_Winter_Project_Week|here]].

==Calendar==

'''''<font color="maroon">The events are listed in the calendar below. Note that due to a current known limitation of our infrastructure, you will need to manually navigate to the week of January 8, 2017 to see the relevant events.</font>'''''<br>

{{#widget:Google Calendar
|id=kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com
|timezone=America/New_York&dates=20170108%2F20170114
|title=NAMIC Winter Project Week
|view=WEEK
|dates=20170108/20170114
}}

iCal (.ics) link: https://calendar.google.com/calendar/ical/kitware.com_sb07i171olac9aavh46ir495c4%40group.calendar.google.com/public/basic.ics

='''Projects'''=

*Use this [[2017_Project_Week_Template | Updated Template for project pages]]

== Deep Learning and GPUs ==
#[[2017 Winter Project Week/Deep Learning for Medical Image Computation| Deep Learning for Medical Image Computing]] (Tina Kapur)
#[[2017 Winter Project Week/Needle Segmentation from MRI | Needle Segmentation from MRI]] (Tina Kapur, Ziyang Wang, Guillaume Pernelle, Paolo Zaffino)
#[[2017 Winter Project Week/DeepInfer| DeepInfer: Open-source Deep Learning Deployment Toolkit]] (Alireza Mehrtash, Mehran Pesteie, Yang (Silvia) Yixin, Tina Kapur, Sandy Wells, Purang Abolmaesumi, Andriy Fedorov)
#[[2017 Winter Project Week/Diffusely abnormal white matter segmentation with 3d U-net| Diffusely abnormal white matter segmentation with 3d U-net]] (Mohsen Ghafoorrian, Bram Platel, Sandy Wells, Tina Kapur, Charles Guttmann)
# [[2017 Winter Project Week/OCM-MRI | Deep Learning for Synthetic MRI]] (Frank Preiswerk, Yaofei "Ada" Wang)
#[[2017 Winter Project Week/An open-source tool to classify TMJ OA condyles | An open-source tool to classify TMJ OA condyles]] (Priscille de Dumast, Juan Carlos Prieto, Beatriz Paniagua)
#[[2017 Winter Project Week/Evaluate Deep Learning for binary cancer legion classification | Evaluate Deep Learning for binary cancer lesion classification]] (Curt Lisle)
#[[2017 Winter Project Week/Convolutional neural nets for lung cancer survival prediction | Convolutional neural nets for lung cancer survival prediction]] (Ahmed Hosny, Chintan Parmar, Roman Zeleznik, Hugo Aerts)
#[[2017 Winter Project Week/Population Based Image Imputation | Population Based Image Imputation]] (Adrian Dalca, Katie Bouman, Mert Sabuncu, Polina Golland)

== Web Technologies ==
#[[2017_Winter_Project_Week/WebTechnologyAndSlicer| Web Technology and Slicer]] (Steve Pieper, Erik Zeigler, Curt Lisle, Satra Ghosh, Hans Meine)
#[[2017 Winter Project Week/Slicer Qt5 and Python3 | Slicer Qt5 and Python3]] (Steve Pieper, Jean-Christophe Fillion-Robin, Andras Lasso, Andrey Fedorov)
#[[2017 Winter Project Week/IPFS_NoSQL_Combination | IPFS and NoSQL for cloud databases]] (Hans Meine, Steve Pieper)
#[[Explore integration of Web-based imaging workflows with Slicer | Explore integration of Web-based imaging workflows with Slicer ]] (Curt Lisle, Satra Gosh, Steve Peiper)
#[[2017 Winter Project Week/Web-based system to federate biological, clinical and morphological data | Web-based system to federate biological, clinical and morphological data]] (Juan Carlos Prieto, Clément Mirabel)
#[[2017_Winter_Project_Week/OAuth2SlicerPathology | OAuth2.0 authentication in SlicerPathology]] (Erich Bremer, Steve Pieper, Teodora Szasz)
#[[2017 Winter Project Week/Electron App to add, navigate and visualize DICOM images | Electron App to add, navigate and visualize DICOM images]] (Smruti Padhy, Satrajit Ghosh, Mathias Goncalves)
#[[2017 Winter Project Week/AMI: A 3D Medical Imaging Javascript Library | AMI: A 3D Medical Imaging Javascript Library]] (Rudolph Pienaar, Jorge Luis Bernal Rusiel, Nicolas Rannou)
#[[2017_Winter_Project_Week/MedicalVisualizerUsingParaViewWeb | Medical Visualizer using ParaViewWeb]] (Teodora Szasz)

== IGT: Navigation, Robotics, Surgical Planning ==
#[[2017 Winter Project Week/Tracked Ultrasound Standardization | Tracked Ultrasound Standardization III: The Refining]] (Andras Lasso, Simon Drouin, Junichi Tokuda, Longquan Chen, Adam Rankin, Janne Beate Bakeng)
#[[2017 Winter Project Week/ROS Surface Scan | ROS Surface Scan]] (Tobias Frank, Junichi Tokuda, Longquan Chen)
#[[2017 Winter Project Week/Open_Source_Electromagnetic_Trackers | Open Source Electromagnetic Trackers]] (Peter Traneus Anderson)
#[[2017 Winter Project Week/LiverResectionPlanning | Liver resection planning extension]] (Louise Oram, Andrey Fedorov, Christian Herz, Andras Lasso)
#[[2017 Winter Project Week/3DSurgicalPlanningBreastReconstruction| 3D surgical planning solution for autologous breast reconstruction]] (Michael Chae, Andras Lasso, Julian Smith, Warren Rozen, David Hunter-Smith)
#[[2017 Winter Project Week/Intraoperative_Functional_Visualization | Visualization Concept for Intraoperative Use of Functional Mapping Data ]] (Rebekka Lauer, Anna Roethe, Prashin Unadkat, Sarah Frisken)

==dMRI==
#[[2017 Winter Project Week/WhiteMatterAnalysis | Fiber endpoint analysis for neurosurgical planning]] (Fan Zhang, Shun Gong, Isaiah Norton, Ye Wu, Lauren J. O'Donnell)
#[[2017 Winter Project Week/LORDWI | Density-based DMRI registration ]] (Henrik Groenholt Jensen, Lauren J. O'Donnell, Tina Kapur, Fan Zhang, Carl-Fredrik Westin)
#[[2017 Winter Project Week/SlicerDMRIDocumentationAndTesting | SlicerDMRI Testing and Documentation]] (Shun Gong, Ye Wu, Isaiah Norton, Fan Zhang, Lauren J. O'Donnell)
#[[2017 Winter Project Week/DiPy_in_Slicer | DiPy integration in Slicer]] (Isaiah Norton, Lauren J. O'Donnell)
#[[2017 Winter Project Week/DWI_Similarity_Metrics | Identification of information-rich patches in Diffusion-Weighted Images]] (Laurent Chauvin, Fan Zhang, Lauren J. O'Donnell, Matthew Toews)

==Quantitative Imaging Informatics==
#[[2017 Winter Project Week/dcmqi | dcmqi library]] (Andrey Fedorov, Christian Herz, JC, Steve Pieper)
#[[2017 Winter Project Week/QuantitativeReporting | DICOM QuantitativeReporting]] (Christian Herz, Andrey Fedorov, Andras Lasso, Csaba Pinter)
#[[2017 Winter Project Week/PyRadiomics | PyRadiomics library ]] (Joost van Griethuysen, Hugo Aerts, Andrey Fedorov, Steve Pieper, Jean-Christophe Fillion-Robin)
#[[2017 Winter Project Week/PkModeling | PkModeling - DCE Modeling Accuracy and UI/UX Update]] (Andrew Beers)
#[[2017 Winter Project Week/SegWithSubtractionAndModel| Manual Segmentation Module w/ Subtraction Maps + Delaunay Models]] (Andrew Beers)

== Shape Analysis, Segmentation ==
#[[2017 Winter Project Week/SlicerShape | Slicer for Shape Analysis ]] (Beatriz Paniagua)
#[[2017 Winter Project Week/MandibularRegression | Mandibular Shape Regression ]] (Beatriz Paniagua, James Fishbaugh)
#[[2017 Winter Project Week/Slicer_HoloLens | Slicer & HoloLens]] (Adam Rankin, Andras Lasso)
#[[2017 Winter Project Week/HyperspectralOpht | Slicer for Hyperspectral Ophthalmology Analysis ]] (Sungmin Hong)
#[[2017 Winter Project Week/GeodesicSegmentationandLungtumorAnalysis| Geodesic Segmentation and Lung tumor Analysis]] (Patmaa S, Sarthak Pati, Ratheesh k, Mark B, Yong F, Despina K, Ragini V, Christos D)
#[[2017 Winter Project Week/ProstateSectorSegmentation | Prostate Gland Sector Segmentation]] (Anneke Meyer, Andrey Fedorov, Alireza Mehrtash, Christian Hansen)
#[[2017 Winter Project Week/Multi-ModalitySegmentationOfUSandMRImagesForGliomaSurgery | Multi-Modality Segmentation of US- and MR-Images for Glioma Surgery]] (Jennifer Nitsch)
#[[2017 Winter Project Week/MeningiomaSegmentation | Segmentation of meningiomas in structural MR images]] (Satrajit Ghosh, Omar Arnaout)
#[[2017 Winter Project Week/CoronarySegmentationTool| Automatic and Manual Segmentation Tool of Coronary Artery from CTA imaging]] (Haoyin Zhou, Jayender Jagadeesan)

== Infrastructure ==
#[[2017 Winter Project Week/SubjectHierarchyRefactoring | Subject hierarchy single-node refactoring]] (Csaba Pinter)
#[[2017 Winter Project Week/Plastimatch19 | Upgrade Plastimatch extension ]] (Greg Sharp)
#[[2017 Winter Project Week/UpdatingCommunityForums | Updating Community Forums (Discourse, GitHub, Gitter, ???)]] (Andrey Fedorov, Andras Lasso, Steve Pieper, Mike Halle, Isaiah Norton, and The Community)
#[[2017 Winter Project Week/SlicerGeometryModifier | Slicer support for interactive modification of 3D models ]] (Johan Andruejol, Beatriz Paniagua, Andras Lasso)
#[[2017 Winter Project Week/Support_for_volumetric_meshes | Support for volumetric meshes ]] (Alexis Girault, Curtis Lisle, Steve Pieper)
#[[2017 Winter Project Week/Improve_Matlab_integration | Improve Matlab integration ]] (Alexis Girault, Andras Lasso)
#[[2017 Winter Project Week/Integrative_Intraoperative_Interface | Integrative Interface for Intraoperative Software Applications ]] (Rebekka Lauer, Anna Roethe, Prashin Unadkat, Sarah Frisken)

==Training and Dissemination==
#[[2017 Winter Project Week/2017TutorialContest| Tutorial contest]] (Sonia Pujol)
#[[2017 Winter Project Week/2017 NVIDIA Demo Contest|NVIDIA Demo Contest]] (Abdul Halabi, Abel Brown)

==Next project week==
#[[2017 Winter Project Week/Next project week| Next project week]] (Paolo Zaffino, Maria Francesca Spadea, Tina Kapur)

= '''Registrants''' =

Do not add your name to this list - it is maintained by the organizers based on your paid registration. To register, visit this [https://www.regonline.com/2017projectweek registration site].

# Aman Shboul, Zaina :: Old Dominion University
# Aerts, Hugo :: DFCI-Harvard
# Alam, Mahbubul :: Old Dominion University
# Anderson, Peter :: Retired
# Andruejol, Johan :: Kitware, Inc.
# Bakeng, Janne Beate :: SINTEF
# Beers, Andrew :: Massachusetts General Hospital
# Bernal Rusiel, Jorge Luis :: Boston Children's Hospital
# Bremer, Erich :: Stony Brook University
# Burke, Brice :: American University of Antigua College of Medicine
# Cetin Karayumak, Suheyla :: Brigham and Women's Hospital
# Chae, Michael :: Monash University
# Chauvin, Laurent :: ETS
# Dalca, Adrian :: Massachusetts Institute of Technology
# DiPrima, Tammy :: Stony Brook University
# Drouin, Simon :: Montreal Neurological Institute
# Fan, Zhipeng :: Brigham and Women's Hospital
# Fedorov, Andriy :: Brigham and Women's Hospital
# Fillion-Robin, Jean-Christophe :: Kitware, Inc.
# Fishbaugh, James :: New York University
# Frank, Tobias :: Leibniz Universität Hannover
# Frisken, Sarah :: Brigham and Women's Hospital
# García Mato, David :: Queen´s University / Universidad Carlos III de Madrid
# Ghafoorian, Mohsen :: Brigham and Women's Hospital
# Ghosh, Satrajit :: Massachusetts Institute of Technology
# Girault, Alexis :: Kitware, Inc.
# Golland, Polina :: Massachusetts Institute of Technology
# Gollub, Randy :: Massachusetts General Hospital
# Goncalves, Mathias :: Massachusetts Institute of Technology
# Gong, Shun :: Brigham and Women's Hospital
# Guerrier de Dumast, Priscille :: University of Michigan
# Halle, Michael :: Brigham and Women's Hospital
# Harris, Gordon :: Massachusetts General Hospital
# Helba, Brian :: Kitware, Inc.
# Herz, Christian :: Brigham and Women's Hospital
# Hong, Sungmin :: New York University
# Hosny, Ahmed :: Dana-Farber
# Jagadeesan, Jayender :: Brigham and Women's Hospital
# Jarecka, Dorota :: Massachusetts Institute of Technology
# Jensen, Henrik G. :: University of Copenhagen
# Kaczmarzyk, Jakub :: Massachusetts Institute of Technology
# Kapur, Tina :: Brigham and Women's Hospital
# Kennedy, David :: UMass Medical School
# Kikinis, Ron :: Brigham and Women's Hospital
# Lasso, Andras :: PerkLab, Queen's University
# Lauer, Rebekka :: Humboldt University Berlin
# Lisle, Curtis :: KnowledgeVis, LLC
# Mastrogiacomo, Katie :: Brigham and Women's Hospital
# Mateus, D. :: TUM
# Mehrtash, Alireza :: Brigham and Women's Hospital
# Meine, Hans :: University of Bremen
# Meyer, Anneke :: University of Magdeburg
# Miller, James :: GE Research
# Mirabel, Clement :: University of Michigan
# Nitsch, Jennifer :: University of Bremen
# Norton, Isaiah :: Brigham and Women's Hospital
# O'Donnell, Lauren :: Brigham and Women's Hospital
# Oram, Louise :: The Intervention Centre-Oslo University Hospital
# Padhy, Smruti :: Massachusetts Institute of Technology
# Paniagua, Beatriz :: Kitware, Inc.
# Parmar, Chintan :: DFCI-Harvard Medical School
# Peled, Sharon :: Brigham and Women's Hospital
# Pieper, Steve :: Isomics, Inc.
# Pinter, Csaba :: Queen's University
# Preiswerk, Frank :: Brigham and Women's Hospital/Harvard Medical School
# Prieto, Juan :: NIRAL
# Pujol, Sonia :: Brigham and Women's Hospital/Harvard Medical School
# Rankin, Adam :: Robarts Research Institute
# Rheault, Francois :: Université de Sherbrooke
# Roethe, Anna :: Humboldt University / Charité University Hospital Berlin
# Szczepankiewicz, Filip :: Lund University
# Sharp, Gregory :: Massachusetts General Hospital
# Sridharan, Patmaa :: University of Pennsylvania-CBICA
# Szasz, Teodora :: University of Chicago
# Unadkat, Prashin :: Brigham and Women's Hospital
# Van Griethuysen , Joost :: Netherlands Cancer Institute
# Vidyaratne, Lasitha :: Old Dominion University
# Wang, Yaofei :: Brigham and Women's Hospital
# Wang, Ziyang :: Brigham and Women's Hospital
# Wei, Dawei :: Brigham and Women's Hospital
# Westin, Carl-Fredrik :: Brigham and Women's Hospital, Harvard Medical School
# Xu, Wanxin :: Brigham and Women's Hospital
# Yang, Yixin :: Brigham and Women's Hospital
# Ye, Wu :: Brigham and Women's Hospital
# Zaffino, Paolo :: Magna Graecia University of Catanzaro, Italy
# Zeleznik, Roman :: DFCI
# Zhang, Fan :: Brigham and Women's Hospital
# Zhang, Miaomiao :: Massachusetts Institute of Technology
# Zhang, Yuqian :: Brigham and Women's Hospital
# Zhou, Haoyin :: Brigham and Women's Hospital
# Ziegler, Erik :: Open Health Imaging Foundation/Mass General Hospital

2017 Winter Project Week/Population Based Image Imputation

2017-01-09T18:18:19Z

Adalca: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT, MGH
*Katie Bouman, MIT
*Mert Sabuncu, MGH
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.
|


|}

==Background and References==

2017 Winter Project Week

2017-01-09T16:39:55Z

Adalca: /* Learning and GPUs */

__NOTOC__
[[image:PW-Winter2017.png|300px]]

=Welcome to the web page for the 24th Project Week!=

The 24th NA-MIC Project Week open source hackathon is being held during the week of January 9-13, 2017 at MIT. 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:''' January 9-13, 2017.
*'''Location:''' [https://www.google.com/maps/place/MIT:+Computer+Science+and+Artificial+Intelligence+Laboratory/@42.361864,-71.090563,16z/data=!4m2!3m1!1s0x0:0x303ada1e9664dfed?hl=en MIT CSAIL], Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)
*'''Transportation:''' Public transportation is highly encouraged, as no parking permits will be issued by MIT. For a list of local garages, please see [http://web.mit.edu/facilities/transportation/parking/visitors/public_parking.html here]
*'''REGISTRATION:''' Register [https://www.regonline.com/2017projectweek here]. Registration Fee: $330.
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.
*'''Next Project Week:'''' [http://wiki.na-mic.org/Wiki/index.php/2017_Summer_Project_Week June 26-30, 2017, Catanzaro, Italy]

== Introduction ==
The National Alliance for Medical Image Computing (NAMIC), was founded in 2005 and 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], enhancements to the underlying building blocks [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 open source hackathon event called Project Week.

[[Engineering:Programming_Events|Project Week]] is a semi-annual open source hackathon which draws 60-120 researchers. As of August 2014, it is a [http://www.miccai.org/organization 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], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO].

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

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

==Conference Calls for Preparation==

Conference call phone number and notes are available [[TCONS:2017_Winter_Project_Week|here]].

==Calendar==

'''''<font color="maroon">The events are listed in the calendar below. Note that due to a current known limitation of our infrastructure, you will need to manually navigate to the week of January 8, 2017 to see the relevant events.</font>'''''<br>

{{#widget:Google Calendar
|id=kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com
|timezone=America/New_York&dates=20170108%2F20170114
|title=NAMIC Winter Project Week
|view=WEEK
|dates=20170108/20170114
}}

iCal (.ics) link: https://calendar.google.com/calendar/ical/kitware.com_sb07i171olac9aavh46ir495c4%40group.calendar.google.com/public/basic.ics

='''Projects'''=

*Use this [[2017_Project_Week_Template | Updated Template for project pages]]

== Learning and GPUs ==
#[[2017 Winter Project Week/Deep Learning for Medical Image Computation| Deep Learning for Medical Image Computing]] (Tina Kapur)
#[[2017 Winter Project Week/Needle Segmentation from MRI | Needle Segmentation from MRI]] (Tina Kapur, Ziyang Wang, Guillaume Pernelle, Paolo Zaffino)
#[[2017 Winter Project Week/DeepInfer| DeepInfer: Open-source Deep Learning Deployment Toolkit]] (Alireza Mehrtash, Mehran Pesteie, Yang (Silvia) Yixin, Tina Kapur, Sandy Wells, Purang Abolmaesumi, Andriy Fedorov)
#[[2017 Winter Project Week/Diffusely abnormal white matter segmentation with 3d U-net| Diffusely abnormal white matter segmentation with 3d U-net]] (Mohsen Ghafoorrian, Bram Platel, Sandy Wells, Tina Kapur)
# [[2017 Winter Project Week/OCM-MRI | Deep Learning for Synthetic MRI]] (Frank Preiswerk, Yaofei "Ada" Wang)
#[[2017 Winter Project Week/An open-source tool to classify TMJ OA condyles | An open-source tool to classify TMJ OA condyles]] (Priscille de Dumast, Juan Carlos Prieto, Beatriz Paniagua)
#[[2017 Winter Project Week/Evaluate Deep Learning for binary cancer legion classification | Evaluate Deep Learning for binary cancer lesion classification]] (Curt Lisle)
#[[2017 Winter Project Week/Convolutional neural nets for lung cancer survival prediction | Convolutional neural nets for lung cancer survival prediction]] (Ahmed Hosny, Chintan Parmar, Roman Zeleznik, Hugo Aerts)
#[[2017 Winter Project Week/Population Based Image Imputation | Population Based Image Imputation]] (Adrian Dalca, Katie Bouman, Polina Golland)

== Web Technologies ==
#[[2017_Winter_Project_Week/WebTechnologyAndSlicer| Web Technology and Slicer]] (Steve Pieper, Erik Zeigler, Curt Lisle, Satra Ghosh, Hans Meine)
#[[2017 Winter Project Week/Slicer Qt5 and Python3 | Slicer Qt5 and Python3]] (Steve Pieper, Jean-Christophe Fillion-Robin, Andras Lasso, Andrey Fedorov)
#[[2017 Winter Project Week/IPFS_NoSQL_Combination | IPFS and NoSQL for cloud databases]] (Hans Meine, Steve Pieper)
#[[Explore integration of Web-based imaging workflows with Slicer | Explore integration of Web-based imaging workflows with Slicer ]] (Curt Lisle, Satra Gosh, Steve Peiper)
#[[2017 Winter Project Week/Web-based system to federate biological, clinical and morphological data | Web-based system to federate biological, clinical and morphological data]] (Juan Carlos Prieto, Clément Mirabel)
#[[2017_Winter_Project_Week/OAuth2SlicerPathology | OAuth2.0 authentication in SlicerPathology]] (Erich Bremer, Steve Pieper, Teodora Szasz)
#[[2017 Winter Project Week/Electron App to add, navigate and visualize DICOM images | Electron App to add, navigate and visualize DICOM images]] (Smruti Padhy, Satrajit Ghosh, Mathias Goncalves)
#[[2017 Winter Project Week/AMI: A 3D Medical Imaging Javascript Library | AMI: A 3D Medical Imaging Javascript Library]] (Rudolph Pienaar, Jorge Luis Bernal Rusiel, Nicolas Rannou)
#[[2017_Winter_Project_Week/MedicalVisualizerUsingParaViewWeb | Medical Visualizer using ParaViewWeb]] (Teodora Szasz)

== IGT: Navigation, Robotics, Surgical Planning ==
#[[2017 Winter Project Week/Tracked Ultrasound Standardization | Tracked Ultrasound Standardization III: The Refining]] (Andras Lasso, Simon Drouin, Junichi Tokuda, Longquan Chen, Adam Rankin, Janne Beate Bakeng)
#[[2017 Winter Project Week/ROS Surface Scan | ROS Surface Scan]] (Tobias Frank, Junichi Tokuda, Longquan Chen)
#[[2017 Winter Project Week/Open_Source_Electromagnetic_Trackers | Open Source Electromagnetic Trackers]] (Peter Traneus Anderson)
#[[2017 Winter Project Week/LiverResectionPlanning | Liver resection planning extension]] (Louise Oram, Andrey Fedorov, Christian Herz, Andras Lasso)
#[[2017 Winter Project Week/3DSurgicalPlanningBreastReconstruction| 3D surgical planning solution for autologous breast reconstruction]] (Michael Chae, Andras Lasso, Julian Smith, Warren Rozen, David Hunter-Smith)

==dMRI==
#[[2017 Winter Project Week/WhiteMatterAnalysis | Fiber endpoint analysis for neurosurgical planning]] (Fan Zhang, Shun Gong, Isaiah Norton, Ye Wu, Lauren J. O'Donnell)
#[[2017 Winter Project Week/LORDWI | Density-based DMRI registration ]] (Henrik Groenholt Jensen, Lauren J. O'Donnell, Tina Kapur, Fan Zhang, Carl-Fredrik Westin)
#[[2017 Winter Project Week/SlicerDMRIDocumentationAndTesting | SlicerDMRI Testing and Documentation]] (Shun Gong, Ye Wu, Isaiah Norton, Fan Zhang, Lauren J. O'Donnell)
#[[2017 Winter Project Week/DiPy_in_Slicer | DiPy integration in Slicer]] (Isaiah Norton, Lauren J. O'Donnell)
#[[2017 Winter Project Week/DWI_Similarity_Metrics | Identification of information-rich patches in Diffusion-Weighted Images]] (Laurent Chauvin, Fan Zhang, Lauren J. O'Donnell, Matthew Toews)

==Quantitative Imaging Informatics==
#[[2017 Winter Project Week/dcmqi | dcmqi library]] (Andrey Fedorov, Christian Herz, JC, Steve Pieper)
#[[2017 Winter Project Week/QuantitativeReporting | DICOM QuantitativeReporting]] (Christian Herz, Andrey Fedorov, Andras Lasso, Csaba Pinter)
#[[2017 Winter Project Week/PyRadiomics | PyRadiomics library ]] (Joost van Griethuysen, Hugo Aerts, Andrey Fedorov, Steve Pieper, Jean-Christophe Fillion-Robin)
#[[2017 Winter Project Week/PkModeling | PkModeling - DCE Modeling Accuracy and UI/UX Update]] (Andrew Beers)
#[[2017 Winter Project Week/SegWithSubtractionAndModel| Manual Segmentation Module w/ Subtraction Maps + Delaunay Models]] (Andrew Beers)

== Shape Analysis, Segmentation, and Visualization ==
#[[2017 Winter Project Week/SlicerShape | Slicer for Shape Analysis ]] (Beatriz Paniagua)
#[[2017 Winter Project Week/MandibularRegression | Mandibular Shape Regression ]] (Beatriz Paniagua, James Fishbaugh)
#[[2017 Winter Project Week/Slicer_HoloLens | Slicer & HoloLens]] (Adam Rankin, Andras Lasso)
#[[2017 Winter Project Week/HyperspectralOpht | Slicer for Hyperspectral Ophthalmology Analysis ]] (Sungmin Hong)
#[[2017 Winter Project Week/GeodesicSegmentationandLungtumorAnalysis| Geodesic Segmentation and Lung tumor Analysis]] (Patmaa S, Sarthak Pati, Ratheesh k, Mark B, Yong F, Despina K, Ragini V, Christos D)
#[[2017 Winter Project Week/ProstateSectorSegmentation | Prostate Gland Sector Segmentation]] (Anneke Meyer, Andrey Fedorov)
#[[2017 Winter Project Week/Multi-ModalitySegmentationOfUSandMRImagesForGliomaSurgery | Multi-Modality Segmentation of US- and MR-Images for Glioma Surgery]] (Jennifer Nitsch)
#[[2017 Winter Project Week/MeningiomaSegmentation | Segmentation of meningiomas in structural MR images]] (Satrajit Ghosh, Omar Arnaout)
#[[2017 Winter Project Week/CoronarySegmentationTool| Automatic and Manual Segmentation Tool of Coronary Artery from CTA imaging]] (Haoyin Zhou, Jayender Jagadeesan)

== Infrastructure ==
#[[2017 Winter Project Week/SubjectHierarchyRefactoring | Subject hierarchy single-node refactoring]] (Csaba Pinter)
#[[2017 Winter Project Week/Plastimatch19 | Upgrade Plastimatch extension ]] (Greg Sharp)
#[[2017 Winter Project Week/UpdatingCommunityForums | Updating Community Forums (Discourse, GitHub, Gitter, ???)]] (Andrey Fedorov, Andras Lasso, Steve Pieper, Mike Halle, Isaiah Norton, and The Community)
#[[2017 Winter Project Week/SlicerGeometryModifier | Slicer support for interactive modification of 3D models ]] (Johan Andruejol, Beatriz Paniagua, Andras Lasso)
#[[2017 Winter Project Week/Support_for_volumetric_meshes | Support for volumetric meshes ]] (Alexis Girault, Curtis Lisle, Steve Pieper)
#[[2017 Winter Project Week/Improve_Matlab_integration | Improve Matlab integration ]] (Alexis Girault, Andras Lasso)

==Training and Dissemination==
#[[2017 Winter Project Week/2017TutorialContest| Tutorial contest]] (Sonia Pujol)

= '''Registrants''' =

Do not add your name to this list - it is maintained by the organizers based on your paid registration. To register, visit this [https://www.regonline.com/2017projectweek registration site].

# Aman Shboul, Zaina :: Old Dominion University
# Aerts, Hugo :: DFCI-Harvard
# Alam, Mahbubul :: Old Dominion University
# Anderson, Peter :: Retired
# Andruejol, Johan :: Kitware, Inc.
# Bakeng, Janne Beate :: SINTEF
# Beers, Andrew :: Massachusetts General Hospital
# Bernal Rusiel, Jorge Luis :: Boston Children's Hospital
# Bremer, Erich :: Stony Brook University
# Burke, Brice :: American University of Antigua College of Medicine
# Cetin Karayumak, Suheyla :: Brigham and Women's Hospital
# Chae, Michael :: Monash University
# Chauvin, Laurent :: ETS
# Dalca, Adrian :: Massachusetts Institute of Technology
# DiPrima, Tammy :: Stony Brook University
# Drouin, Simon :: Montreal Neurological Institute
# Fan, Zhipeng :: Brigham and Women's Hospital
# Fedorov, Andriy :: Brigham and Women's Hospital
# Fillion-Robin, Jean-Christophe :: Kitware, Inc.
# Fishbaugh, James :: New York University
# Frank, Tobias :: Leibniz Universität Hannover
# Frisken, Sarah :: Brigham and Women's Hospital
# García Mato, David :: Queen´s University / Universidad Carlos III de Madrid
# Ghafoorian, Mohsen :: Brigham and Women's Hospital
# Ghosh, Satrajit :: Massachusetts Institute of Technology
# Girault, Alexis :: Kitware, Inc.
# Golland, Polina :: Massachusetts Institute of Technology
# Gollub, Randy :: Massachusetts General Hospital
# Goncalves, Mathias :: Massachusetts Institute of Technology
# Gong, Shun :: Brigham and Women's Hospital
# Guerrier de Dumast, Priscille :: University of Michigan
# Halle, Michael :: Brigham and Women's Hospital
# Harris, Gordon :: Massachusetts General Hospital
# Helba, Brian :: Kitware, Inc.
# Herz, Christian :: Brigham and Women's Hospital
# Hong, Sungmin :: New York University
# Hosny, Ahmed :: Dana-Farber
# Jagadeesan, Jayender :: Brigham and Women's Hospital
# Jarecka, Dorota :: Massachusetts Institute of Technology
# Jensen, Henrik G. :: University of Copenhagen
# Kaczmarzyk, Jakub :: Massachusetts Institute of Technology
# Kapur, Tina :: Brigham and Women's Hospital
# Kennedy, David :: UMass Medical School
# Kikinis, Ron :: Brigham and Women's Hospital
# Lasso, Andras :: PerkLab, Queen's University
# Lauer, Rebekka :: Humboldt University Berlin
# Lisle, Curtis :: KnowledgeVis, LLC
# Mastrogiacomo, Katie :: Brigham and Women's Hospital
# Mateus, D. :: TUM
# Mehrtash, Alireza :: Brigham and Women's Hospital
# Meine, Hans :: University of Bremen
# Meyer, Anneke :: University of Magdeburg
# Miller, James :: GE Research
# Mirabel, Clement :: University of Michigan
# Nitsch, Jennifer :: University of Bremen
# Norton, Isaiah :: Brigham and Women's Hospital
# O'Donnell, Lauren :: Brigham and Women's Hospital
# Oram, Louise :: The Intervention Centre-Oslo University Hospital
# Padhy, Smruti :: Massachusetts Institute of Technology
# Paniagua, Beatriz :: Kitware, Inc.
# Parmar, Chintan :: DFCI-Harvard Medical School
# Peled, Sharon :: Brigham and Women's Hospital
# Pieper, Steve :: Isomics, Inc.
# Pinter, Csaba :: Queen's University
# Preiswerk, Frank :: Brigham and Women's Hospital/Harvard Medical School
# Prieto, Juan :: NIRAL
# Pujol, Sonia :: Brigham and Women's Hospital/Harvard Medical School
# Rankin, Adam :: Robarts Research Institute
# Rheault, Francois :: Université de Sherbrooke
# Roethe, Anna :: Humboldt University / Charité University Hospital Berlin
# Szczepankiewicz, Filip :: Lund University
# Sharp, Gregory :: Massachusetts General Hospital
# Sridharan, Patmaa :: University of Pennsylvania-CBICA
# Szasz, Teodora :: University of Chicago
# Unadkat, Prashin :: Brigham and Women's Hospital
# Van Griethuysen , Joost :: Netherlands Cancer Institute
# Vidyaratne, Lasitha :: Old Dominion University
# Wang, Yaofei :: Brigham and Women's Hospital
# Wang, Ziyang :: Brigham and Women's Hospital
# Wei, Dawei :: Brigham and Women's Hospital
# Westin, Carl-Fredrik :: Brigham and Women's Hospital, Harvard Medical School
# Xu, Wanxin :: Brigham and Women's Hospital
# Yang, Yixin :: Brigham and Women's Hospital
# Ye, Wu :: Brigham and Women's Hospital
# Zaffino, Paolo :: Magna Graecia University of Catanzaro, Italy
# Zeleznik, Roman :: DFCI
# Zhang, Fan :: Brigham and Women's Hospital
# Zhang, Miaomiao :: Massachusetts Institute of Technology
# Zhang, Yuqian :: Brigham and Women's Hospital
# Zhou, Haoyin :: Brigham and Women's Hospital
# Ziegler, Erik :: Open Health Imaging Foundation/Mass General Hospital

2017 Winter Project Week/Population Based Image Imputation

2017-01-09T16:38:50Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT
*Katie Bouman, MIT
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.
|


|}

==Background and References==

2017 Winter Project Week/Population Based Image Imputation

2017-01-09T16:38:02Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT
*Katie Bouman, MIT
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.

*
|}

==Background and References==

File:PW-Imputation2017.png

2017-01-09T16:37:17Z

Adalca:

2017 Winter Project Week/Population Based Image Imputation

2017-01-09T16:22:39Z

Adalca: adding new project

__NOTOC__
<gallery>
Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]

Image:PW-Imputation2017.png
</gallery>

==Key Investigators==
*Adrian Dalca, MIT
*Katie Bouman, MIT
*Polina Golland, MIT

==Project Description==

We developed a model for image imputation - or restoration - for clinical quality images where slice separation (e.g. 6mm) is significantly larger than slice resolution (e.g. 1mm^2). Our model captures statistical correlations within a collection of clinical images from a population of subjects at each location in the image. This means we learn different model parameters for many image locations involving methematical updates that involve many small matrix multiplications. In this project we want to investigate the potential for GPUs to help in the runtime of the algorithm.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* To test (and implement) a GPU version of Population Based Image Imputation, which learns a sparse-observation low-dimensional Gaussian Mixture Model at many locations in an image.
|

* Test whether the type of operations we do (most many many small matrix multiplications and look-up) can be made significantly more efficient on a GPU
* Implement algorithm updates on GPU
* investigate banding side-effects.|

*
|}

==Background and References==

2016 Winter Project Week/Projects/PatchRegistration

2016-01-08T15:10:10Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:MRFRegresult.png|Current Resulting registration on isotropic Buckner images illustrated via segmentation overlap from an atlas.
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Andreea Bobu (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail.
In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions.
Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
|

* We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images
* We'll develop the infrastracture and evaluate the current metric on isotropic data at large.
* We'll develop a new metric for sparse images and test it out.
|

* We set up registration on a buckner40 dataset with a large number of parameters and launched on a large cluster
* We found a global setting that yields very good results, with volume overlap (DICE) of most subcortical structures in the 80s and 90s.
* Results shown above
|}

File:MRFRegresult.png

2016-01-08T15:09:13Z

Adalca:

2016 Winter Project Week/Projects/PatchRegistration

2016-01-08T15:08:30Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:MRFRegresult.png|Clinical Stroke Image
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Andreea Bobu (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail.
In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions.
Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
|

* We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images
* We'll develop the infrastracture and evaluate the current metric on isotropic data at large.
* We'll develop a new metric for sparse images and test it out.
|

* We set up registration on a buckner40 dataset with a large number of parameters and launched on a large cluster
* We found a global setting that yields very good results, with volume overlap (DICE) of most subcortical structures in the 80s and 90s.
* Results shown above
|}

File:GmmResult2.png

2016-01-08T14:09:55Z

Adalca:

2016 Winter Project Week/Projects/ImageRestoration

2016-01-08T14:09:22Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:gmm_interp.png|Running result: Original (linear-interp) data | our gmm-based interp | "true" high res data
Image:gmmResult2.png|More results show our ability to improve images, but only on small areas.
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Katie Bouman (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<strong>Essentially, we explore a model where for a given location in all volumes of a dataset, we model those image patches as drawn from a particular mixture model.</strong>

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data.
|

* We've implemented a small version of the model without regularization and that only works on a small section of a volume. We'll try to deploy it on large-scale dataset on entire volumes.
|

* We've built infrastructure for deploying the training at each location in parallele
* We've used our lab's cluster to deploy training with various parameter at each of 18,000 locations
* We've coded reconstruction modules to rebuild each region, but still need to combine each of the reconstructions.
|}

2016 Winter Project Week/Projects/ImageRestoration

2016-01-04T18:43:52Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:gmm_interp.png|Running result: Original (linear-interp) data | our gmm-based interp | "true" high res data
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Katie Bouman (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<strong>Essentially, we explore a model where for a given location in all volumes of a dataset, we model those image patches as drawn from a particular mixture model.</strong>

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data.
|

* We've implemented a small version of the model without regularization and that only works on a small section of a volume. We'll try to deploy it on large-scale dataset on entire volumes.
|

*
|}

2016 Winter Project Week/Projects/ImageRestoration

2016-01-04T18:42:34Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:gmm_interp.png|Current Result: Original (linear-interpolated) data | our gmm-based interpolation | "true" high resolution data
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Katie Bouman (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<strong>Essentially, we explore a model where for a given location in all volumes of a dataset, we model those image patches as drawn from a particular mixture model.</strong>

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data.
|

* We've implemented a small version of the model without regularization and that only works on a small section of a volume. We'll try to deploy it on large-scale dataset on entire volumes.
|

*
|}

2016 Winter Project Week/Projects/ImageRestoration

2016-01-04T18:22:12Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:gmm_interp.png|Current Result: Original (linear-interpolated) data | our gmm-based interpolation | "true" high resolution data
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Katie Bouman (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data.
|

* We've implemented a small version of the model without regularization and that only works on a small section of a volume. We'll try to deploy it on large-scale dataset on entire volumes.
|

*
|}

2016 Winter Project Week/Projects/PatchRegistration

2016-01-04T18:20:10Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Andreea Bobu (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail.
In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions.
Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
|

* We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images

* We'll develop a new metric for sparse images and test it out.
|

*
|}

File:Gmm interp.png

2016-01-04T03:29:05Z

Adalca:

2016 Winter Project Week/Projects/ImageRestoration

2016-01-04T03:28:28Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:gmm_interp.png|Current Result: Original (linear-interpolated) data | our gmm-based interpolation | "true" high resolution data
</gallery>

==Key Investigators==
*Adrian Dalca (MIT)
*Katie Bouman (MIT)
*Polina Golland (MIT)

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

{| class="wikitable"
! style="text-align: left; width:27%" | Objective
! style="text-align: left; width:27%" | Approach and Plan
! style="text-align: left; width:27%" | Progress and Next Steps
|- style="vertical-align:top;"
|

* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data.
|

*
|

*
|}

2016 Winter Project Week

2015-12-09T17:35:29Z

Adalca: /* Projects */

__NOTOC__

[[image:PW-MIT2016.png|300px|left]]
<br><br><br><br><br><br><br><br><br><br><br><br>
'''Dates:''' January 4-8, 2016

'''Location:''' MIT, Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)

'''REGISTRATION:''' Register [https://www.regonline.com/namic16 here].
<br>

== Introduction ==
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], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO].

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]

==Agenda==

Tentative Agenda

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Monday, January 4
!style="width:18%" |Tuesday, January 5
!style="width:18%" |Wednesday, January 6
!style="width:18%" |Thursday, January 7
!style="width:18%" |Friday, January 8
|-
|
|bgcolor="#dbdbdb"|'''Project Presentations'''
|bgcolor="#6494ec"|
|
|bgcolor="#88aaae"|'''IGT Day'''
|bgcolor="#faedb6"|'''Reporting Day'''
|-
|bgcolor="#ffffdd"|'''8:30am'''
|
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|-
|bgcolor="#ffffdd"|'''9am-12pm'''
|'''10:30am-12pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 1 by Sarang Joshi)<br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].
|'''10-11:30am:''' <font color="#503020">Breakout Session: New Slicer Extensions'''</font><br>
|
'''10-11:30am:''' <font color="#503020">Breakout Session: [[2015_Winter_Project_Week:SlicerROSIntegration| Slicer for Medical Robotics Research]] </font>
<br>
|'''9:00-10:30am''' TBD <br>
<br>----------------------------------------<br>
'''10am-12pm: <font color="#4020ff">Breakout Session:'''</font><br>TBD <br>
|'''10am-12pm:''' [[#Projects|Project Progress Updates]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''12pm''' [[Events:TutorialContestJanuary2016|Tutorial Contest Winner Announcement]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|-
|bgcolor="#ffffdd"|'''12pm-1pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch boxes; Adjourn by 1:30pm
|-
|bgcolor="#ffffdd"|'''1pm-5:30pm'''
|'''1-1:05pm: <font color="#503020">Welcome</font>'''<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''1:05-2:30pm:''' [[#Projects|Project Introductions]] (all Project Leads)<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''2:45-4pm:''' [[Breakout Session: Ultrasound]]
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>

'''4:00pm-5:30pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 2 by Sarang Joshi) <br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].
|'''1-3pm:''' <font color="#503020"> [[Breakout Session: What's Planned for Slicer Core]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|'''1-2:30pm:''' <font color="#503020">Breakout Session:'''</font><br>[[Breakout Session: Diffusion MRI]]
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|
|
|-
|bgcolor="#ffffdd"|'''5:30pm'''
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|
|}

<googlecalendar>kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com</googlecalendar>

='''Projects'''=
* [[2016_Project_Week_Template | Template for project pages]]

* [[2015_Winter_Project_Week:SlicerROSIntegration | 3D Slicer + ROS Integration]] (Junichi Tokuda, Axel Krieger, Simon Leonard)
* [[2016_Winter_Project_Week:TrackedUltrasoundStandardization | Tracked ultrasound standardization]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Steve Pieper, Adam Rankin)
*Integration of CustusX with PLUS on BK System (Christian A, Adam Rankin)
*Integration of ImFusion MR-US registration with BWH AMIGO neurosurgery setup (Christian A, Tina Kapur, Steve Pieper, Sandy Wells, Andras Lasso)
*Digital Pathology Nuclear Segmentation (Erich Bremer, Nicole Aucoin)
*Chest Imaging Platform: COPD and other pulmonary diseases (Raúl San José, Jorge Onieva)
*Upgrade the namic (and Slicer?) wiki (JC, Mike Halle)
* [[2016_Winter_Project_Week:BatchImageAnalysis | Batch Clinical Image Analysis]] (Kalli Retzepi, Yangming Ou, Matt Toews, Steve Pieper, Sandy Wells, Randy Gollub)
* [[2016_Winter_Project_Week:ImageRestoration | Image Restoration via Patch GMMs]] (Adrian Dalca, Katie Bouman, Polina Golland)
* [[2016_Winter_Project_Week:PatchRegistration | Patch Based Discrete Registration for Difficult Images]] (Adrian Dalca, Andreea Bobu, Polina Golland)

==Infrastructure==
* [[2016_Winter_Project_Week:SlicerProjectName | Project Name]] (List of people working on this project)
* [[2016_Winter_Project_Week:CommonGL | CommonGL]] (Steve Pieper, Jim Miller)
* [[2016_Winter_Project_Week:WebTechnologies | Web Technologies and Slicer]] (Steve Pieper, Hans Meine)
* [[2016_Winter_Project_Week:CLIModules Backgrounding in MeVisLab | Running CLI Modules in MeVisLab asynchronously]] (Hans Meine)
* [[2016_Winter_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with BRAINSFit (or other interesting CLIs) in MeVisLab]] (Hans Meine, Steve Pieper)
* [[2016_Winter_Project_Week:CLI_Dashboard | Kibana dashboard for browsing all available CLI modules]] (Hans Meine, JC?)
* [[2016_Winter_Project_Week:SegmentationEditorWidget | Editor widget using Segmentations]] (Csaba Pinter, Andras Lasso, Andrey Fedorov, Steve Pieper?)
* [[2016_Winter_Project_Week:DICOMSegObjIntegration | Integration of DICOM SegObj with Segmentations]] (Kyle Sunderland, Csaba Pinter, Andras Lasso, Andrey Fedorov, Steve Pieper?)
* [[2016_Winter_Project_Week:CondaSlicer | Integration of Anaconda Python in Slicer]] (JC, Raúl San José, Jorge Onieva, Slicer Community?)
* [[2016_Winter_Project_Week:Data Persisting | Mechanism to persist clinical user data from different modules based on SQLite and/or other database engines ]] (Raúl San José, Jorge Onieva)
* [[2016_Winter_Project_Week:Workflows | Workflow module that enables the navigation and data sharing between different modules in a clinical workflow ]] (Raúl San José, Jorge Onieva)

= '''Logistics''' =

*'''Dates:''' January 4-8, 2016
*'''Location:''' MIT, Kiva Conference room; 4th floor of Building 32.
*'''REGISTRATION:''' Register [https://www.regonline.com/namic16 here].
*'''Registration Fee:''' $300.
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.
*'''Room sharing''': If interested, add your name to the list [[2016_Winter_Project_Week/RoomSharing|here]]

= '''Registrants''' =

Do not add your name to this list - it is maintained by the organizers based on your paid registration. To register, visit [https://www.regonline.com/namic16 this registration url].

2016 Winter Project Week/Projects/PatchRegistration

2015-12-09T17:35:12Z

Adalca: Created page with '__NOTOC__ <gallery> Image:PW-MIT2016.png|Projects List Image:WMH_T1.png|Clinical Stroke Image </gallery> ==Key Investigators== - Adrian Dal…'

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Andreea Bobu, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail.
In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions.
Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
</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 Winter Project Week/Projects/ImageRestoration

2015-12-09T17:34:43Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Katie Bouman, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data..
</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 Winter Project Week/Projects/ImageRestoration

2015-12-09T17:34:34Z

Adalca: Created page with '__NOTOC__ <gallery> Image:PW-MIT2015.png|Projects List Image:WMH_T1.png|Clinical Stroke Image </gallery> ==Key Investigators== - Adrian Dal…'

__NOTOC__
<gallery>
Image:PW-MIT2015.png|[[2016_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Katie Bouman, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data..
</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>

2015 Winter Project Week:PatchRegistration

2015-12-07T15:38:22Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2015.png|[[2015_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Andreea Bobu, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail.
In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions.
Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
</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>

2015 Winter Project Week:ImageRestoration

2015-12-07T15:35:10Z

Adalca: Created page with '__NOTOC__ <gallery> Image:PW-MIT2015.png|Projects List Image:WMH_T1.png|Clinical Stroke Image </gallery> ==Key Investigators== - Adrian Dal…'

__NOTOC__
<gallery>
Image:PW-MIT2015.png|[[2015_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Katie Bouman, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data..
</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>

2015 Winter Project Week:PatchRegistration

2015-12-07T15:34:40Z

Adalca: Created page with '__NOTOC__ <gallery> Image:PW-MIT2015.png|Projects List Image:WMH_T1.png|Clinical Stroke Image </gallery> ==Key Investigators== - Adrian Dal…'

__NOTOC__
<gallery>
Image:PW-MIT2015.png|[[2015_Winter_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
</gallery>

==Key Investigators==
- Adrian Dalca, Katie Bouman, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Most synthesis, in-painting or super-resolution methods require a training dataset which includes the desired-quality images. Unfortunately, in the clinical setting this is often now available.

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail.

To improve results for large datasets of clinical-quality data, we are investigating restoration methods without training datasets. Here, we are using a patch-based Gaussian Mixture Model approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate a current model for learning and using Patch-based Gaussian Mixture Model to restore sparse-slice data..
</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 Winter Project Week

2015-12-07T15:30:31Z

Adalca:

__NOTOC__

[[image:PW-MIT2016.png|300px|left]]
<br><br><br><br><br><br><br><br><br><br><br><br>
'''Dates:''' January 4-8, 2016

'''Location:''' MIT, Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)
<br>

== Introduction ==
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], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO].

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]

==Agenda==

Tentative Agenda

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Monday, January 4
!style="width:18%" |Tuesday, January 5
!style="width:18%" |Wednesday, January 6
!style="width:18%" |Thursday, January 7
!style="width:18%" |Friday, January 8
|-
|
|bgcolor="#dbdbdb"|'''Project Presentations'''
|bgcolor="#6494ec"|
|
|bgcolor="#88aaae"|'''IGT Day'''
|bgcolor="#faedb6"|'''Reporting Day'''
|-
|bgcolor="#ffffdd"|'''8:30am'''
|
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|-
|bgcolor="#ffffdd"|'''9am-12pm'''
|'''10:30am-12pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 1 by Sarang Joshi)<br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].
|'''10-11:30am:''' <font color="#503020">Breakout Session: New Slicer Extensions'''</font><br>
|
'''10-11:30am:''' <font color="#503020">Breakout Session: [[2015_Winter_Project_Week:SlicerROSIntegration| Slicer for Medical Robotics Research]] </font>
<br>
|'''9:00-10:30am''' TBD <br>
<br>----------------------------------------<br>
'''10am-12pm: <font color="#4020ff">Breakout Session:'''</font><br>TBD <br>
|'''10am-12pm:''' [[#Projects|Project Progress Updates]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''12pm''' [[Events:TutorialContestJune2014|Tutorial Contest Winner Announcement]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|-
|bgcolor="#ffffdd"|'''12pm-1pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch boxes; Adjourn by 1:30pm
|-
|bgcolor="#ffffdd"|'''1pm-5:30pm'''
|'''1-1:05pm: <font color="#503020">Welcome</font>'''<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''1:05-2:30pm:''' [[#Projects|Project Introductions]] (all Project Leads)<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>
'''2:45-4pm:''' [[Breakout Session: Ultrasound]]
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
<br>----------------------------------------<br>

'''4:00pm-5:30pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 2 by Sarang Joshi) <br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].
|'''1-3pm:''' <font color="#503020"> [[Breakout Session: What's Planned for Slicer Core]]<br>
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|'''1-2:30pm:''' <font color="#503020">Breakout Session:'''</font><br>[[Breakout Session: Diffusion MRI]]
[[MIT_Project_Week_Rooms#Kiva|Kiva]]
|
|
|-
|bgcolor="#ffffdd"|'''5:30pm'''
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|
|}

<googlecalendar>kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com</googlecalendar>

='''Projects'''=
* [[2016_Project_Week_Template | Template for project pages]]

* [[2015_Winter_Project_Week:SlicerROSIntegration | 3D Slicer + ROS Integration]] (Junichi Tokuda, Axel Krieger, Simon Leonard)
* [[2016_Winter_Project_Week:TrackedUltrasoundStandardization | Tracked ultrasound standardization]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Steve Pieper, Adam Rankin)
*Integration of CustusX with PLUS on BK System (Christian A, Adam Rankin)
*Integration of ImFusion MR-US registration with BWH AMIGO neurosurgery setup (Christian A, Tina Kapur, Steve Pieper, Sandy Wells, Andras Lasso)
*Digital Pathology Nuclear Segmentation (Erich Bremer, Nicole Aucoin)
*Chest Imaging Platform: COPD and other pulmonary diseases (Raúl San José, Jorge Onieva)
*Upgrade the namic wiki (JC, Mike Halle)
* [[2016_Winter_Project_Week:BatchImageAnalysis | Batch Clinical Image Analysis]] (Kalli Retzepi, Yangming Ou, Matt Toews, Steve Pieper, Sandy Wells, Randy Gollub)
* [[2015_Winter_Project_Week:ImageRestoration | Image Restoration via Patch GMMs]] (Adrian Dalca, Katie Bouman, Polina Golland)
* [[2015_Winter_Project_Week:PatchRegistration | Patch Based Discrete Registration for Difficult Images]] (Adrian Dalca, Andreea Bobu, Polina Golland)

==Infrastructure==
* [[2016_Winter_Project_Week:SlicerProjectName | Project Name]] (List of people working on this project)
* [[2016_Winter_Project_Week:CommonGL | CommonGL]] (Steve Pieper, Jim Miller)
* [[2016_Winter_Project_Week:WebTechnologies | Web Technologies and Slicer]] (Steve Pieper, Hans Meine)
* [[2016_Winter_Project_Week:CLIModules Backgrounding in MeVisLab | Running CLI Modules in MeVisLab asynchronously]] (Hans Meine)
* [[2016_Winter_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with BRAINSFit (or other interesting CLIs) in MeVisLab]] (Hans Meine, Steve Pieper)
* [[2016_Winter_Project_Week:CLI_Dashboard | Kibana dashboard for browsing all available CLI modules]] (Hans Meine, JC?)
* [[2016_Winter_Project_Week:SegmentationEditorWidget | Editor widget using Segmentations]] (Csaba Pinter, Andras Lasso, Steve Pieper?)

= '''Logistics''' =

*'''Dates:''' January 4-8, 2016
*'''Location:''' MIT, Kiva Conference room; 4th floor of Building 32.
*'''REGISTRATION:''' Register [https://www.regonline.com/namic16 here].
*'''Registration Fee:''' $300.
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.
*'''Room sharing''': If interested, add your name to the list [[2016_Winter_Project_Week/RoomSharing|here]]

= '''Registrants''' =

Do not add your name to this list - it is maintained by the organizers based on your paid registration.

2014 Summer Project Week:Stroke-SuperResolution

2014-06-27T14:40:27Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
Image:STROKE_SR3.png| Top: Original, downsampled(input); Bottom results: NLM, us (before), us (now)
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail. To improve results for large datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Several improvements (i.e. bug fixes :) ) as well as an implementation of scale-space has been done
* Changes helped significantly on simulated data. See result image.
* Trying to apply algorithm to new datasets: [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
</div>
</div>

File:STROKE SR3.png

2014-06-27T14:39:39Z

Adalca:

2014 Summer Project Week:Stroke-SuperResolution

2014-06-27T14:39:22Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
Image:STROKE_SR3.png|Bottom results: NLM, Us (before), US (now)
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail. To improve results for large datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Several improvements (i.e. bug fixes :) ) as well as an implementation of scale-space has been done
* Changes helped significantly on simulated data. See result image.
* Trying to apply algorithm to new datasets: [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
</div>
</div>

2014 Summer Project Week:Stroke-SuperResolution

2014-06-27T14:34:47Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail. To improve results for large datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Several improvements (i.e. bug fixes :) ) as well as an implementation of scale-space has been done
* Changes helped significantly on simulated data. See result image.
* Trying to apply algorithm to new datasets: [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
</div>
</div>

2014 Summer Project Week:Stroke-ImagingGenetics

2014-06-27T14:33:42Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:Leuk_model.png|Leukoaraiosis Model
</gallery>

==Key Investigators==
* Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT
* Natalia Rost, Jonathan Rosand, MGH

==Project Description==
<div style="margin: 20px;">
This is one of a series of projects on a large clinical dataset of stroke patients, including T2-FLAIR and DWI imaging, and genetic information. The ultimate goal is to investigate clinical and genetic causes affecting stroke outcome and small vessel disease. We recently (MICCAI 2014) developed a leukoaraiosis (small vessel disease) probabilistic co-variation model for T2-FLAIR, which we use to differentiate between small vessel disease and acute or chronic stroke. In this work, we wish to investigate the possible genetic and clinical effects related to this model.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://people.csail.mit.edu/adalca/stroke/tipix/mean_leuk/mainSubVol__$.png&xBins=256&nDims=1&debug=true: Average Leukoaraiosis projection]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://people.csail.mit.edu/adalca/stroke/tipix/leuk_span/x_$.nii.gz&xBins=1&nDims=1&debug=true: Explore the first component of the model]

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Here, we wish to investigate the parameters of the model as potential phenotypes against for clinical and genetic analyses.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We will create the phenotype projections for ~80 stroke patients and experiment with correlating the genetic and clinical factors.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Run the projection on 100 projections.
* Feedback on looking at imaging genetics
* Genetics data needs significant processing.
</div>
</div>

File:MipiX 2.png

2014-06-27T14:08:45Z

Adalca:

2014 Summer Project Week:mipiX

2014-06-27T14:08:28Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX]
Image:mipiX_2.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/leuk/reg$_$.png&nDims=2&xBins=13&yBins=2&debug=true Time series demo]
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
Discussions led to:
* need support for multiple-sized images
* need support for various input types
* need support for more high dimensions, or fast switching between dimensions. We are considering use of mouse wheel.
Features implemented
* Support for (individual) mask files has been implemented and tested, although not yet in the full framework
* blending between images implemented
* started work on a simple GUI.
* investigated CamanJS for image control.
</div>
</div>

2014 Summer Project Week:Stroke-ImagingGenetics

2014-06-26T22:23:12Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:Leuk_model.png|Leukoaraiosis Model
</gallery>

==Key Investigators==
* Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT
* Natalia Rost, Jonathan Rosand, MGH

==Project Description==
<div style="margin: 20px;">
This is one of a series of projects on a large clinical dataset of stroke patients, including T2-FLAIR and DWI imaging, and genetic information. The ultimate goal is to investigate clinical and genetic causes affecting stroke outcome and small vessel disease. We recently (MICCAI 2014) developed a leukoaraiosis (small vessel disease) probabilistic co-variation model for T2-FLAIR, which we use to differentiate between small vessel disease and acute or chronic stroke. In this work, we wish to investigate the possible genetic and clinical effects related to this model.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://people.csail.mit.edu/adalca/stroke/tipix/mean_leuk/mainSubVol__$.png&xBins=256&nDims=1&debug=true: Average Leukoaraiosis projection]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://people.csail.mit.edu/adalca/stroke/tipix/leuk_span/x_$.nii.gz&xBins=1&nDims=1&debug=true: Explore the first component of the model]

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* Here, we wish to investigate the parameters of the model as potential phenotypes against for clinical and genetic analyses.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We will create the phenotype projections for ~80 stroke patients and experiment with correlating the genetic and clinical factors.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* We've gotten some feedback on looking at imaging genetics, and run the projection on 100 projections. The genetics, however, needs much more processing.
</div>
</div>

2014 Summer Project Week:mipiX

2014-06-26T22:02:06Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/leuk/reg$_$.png&nDims=2&xBins=13&yBins=2&debug=true Time series demo]
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
Discussions led to:
* need support for multiple-sized images
* need support for various input types
* need support for more high dimensions, or fast switching between dimensions. We are considering use of mouse wheel.
Features implemented
* Support for (individual) mask files has been implemented and tested, although not yet in the full framework
* blending between images implemented
* started work on a simple GUI.
* investigated CamanJS for image control.
</div>
</div>

2014 Summer Project Week:Stroke-SuperResolution

2014-06-26T21:56:26Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail. To improve results for large datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
* Several improvements as well as an implementation of scale-space has been done, which has helped significantly on simulated data. See result image.
* Trying to apply algorithm to new datasets: [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
</div>
</div>

File:STROKE SR2.png

2014-06-26T21:53:35Z

Adalca:

File:STROKE SR1.png

2014-06-25T19:50:41Z

Adalca: uploaded a new version of "File:STROKE SR1.png"

2014 Summer Project Week:mipiX

2014-06-23T17:42:04Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/leuk/reg$_$.png&nDims=2&xBins=13&yBins=2&debug=true Time series demo]
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:mipiX

2014-06-23T16:12:25Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/leuk/reg$_$.png&nDims=2&xBins=13&yBins=2&debug=true Time series demo]
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:mipiX

2014-06-23T16:08:09Z

Adalca: /* Project Description */

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:Stroke-ImagingGenetics

2014-06-23T16:07:12Z

Adalca: /* Project Description */

2014 Summer Project Week:Stroke-SuperResolution

2014-06-23T16:04:31Z

Adalca: /* Project Description */

2014 Summer Project Week:Stroke-SuperResolution

2014-06-23T16:02:14Z

Adalca:

2014 Summer Project Week:Stroke-SuperResolution

2014-06-23T14:59:16Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
To improve results for Large Datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:Stroke-SuperResolution

2014-06-23T14:40:06Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
To improve results for Large Datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We will investigate/implement a scale-space MRF inference based on patch search results.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* We are developing a [https://github.com/adalca/patchlib| patch library in MATLAB] and applying it to a large stroke dataset
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:mipiX

2014-06-23T14:34:07Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://goo.gl/EQ9iLt Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo]

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>

2014 Summer Project Week:mipiX

2014-06-23T14:33:51Z

Adalca:

__NOTOC__
<gallery>
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly : mipiX]
</gallery>

==Key Investigators==
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT

==Project Description==
<div style="margin: 20px;">
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.

[http://goo.gl/EQ9iLt: Lupus Dataset Demo]

[http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1#: ADNI Demo]

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
* We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
* The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
*
</div>
</div>