NAMIC Wiki - User contributions [en]

ITK Image Registration with CUDA

2008-01-17T10:47:50Z

Nicky: /* Description */

=Description=
This page explains the details of ITK registration using CUDA.

==Objective==
The objective of this project is to Integrate GPU accelerated rigid and non-rigid registration on CUDA platform into ITK framework.

==Framework==
The registration framework is shown in the following figure.

[[Image:itkcudaregistration.jpg|700px]]

Registration framework should not violate the existing itk registration framework, so that user will use itk cuda classes the same way as existing itk classes. itkCudaMemory classes provides the interface for GPU memory the same way as are implemented in vtkCudaMemory classes.

==ITK CUDA classes==
* itkCudaMemory classes
* itkCudaImageToImageMetric and its derivatives
* itkCudaTransform and its derivatives
* itkCudaInterpolateImageFunction and its derivatives

File:Itkcudaregistration.jpg

2008-01-17T10:31:41Z

Nicky: ITK CUDA registration framework

ITK CUDA registration framework

ITK Image Registration with CUDA

2008-01-17T10:31:00Z

Nicky: /* Description */

ITK Image Registration with CUDA

2008-01-15T13:06:17Z

Nicky:

ITK Image Registration with CUDA

2008-01-15T12:54:43Z

Nicky: New page: =Description= This page explains the details of ITK registration using CUDA. ==Objective== Integrating GPU accelerated rigid and non-rigid registration on CUDA platform into ITK framework...

=Description=
This page explains the details of ITK registration using CUDA.

==Objective==
Integrating GPU accelerated rigid and non-rigid registration on CUDA platform into ITK framework.

Slicer-IGT/GPU-IGT

2008-01-15T12:49:07Z

Nicky: /* Timeline/Progress */

=Objective=
*To integrate fast GPU-accerelated image processing in NA-MIC toolkit
*To perform 4D MRI or US guided operation assisted by GPU-accelerated Slicer
*Create a Wiki Page for [[Slicer3:Volume Rendering With Cuda]]

=People involved=
*Nobuhiko Hata (BWH)
*Benjamin Grauer (BWH, ETH)
*Nicholas Herlambang (Tokyo University)
*Wong Ki Jeong (U Utah)

=Events=

* [http://wiki.na-mic.org/Wiki/index.php/Slicer-IGT/GPU-IGT/112707 T-con Nov 27, 2007]
* [http://wiki.na-mic.org/Wiki/index.php/Slicer-IGT/GPU-IGT/121107 Dec 11, 2007 at 930am Boston time]
* Salt-Lake city NA-MIC AHM, Jan 11-, 2008
* [[Slicer-IGT:GPU-IGT:01/09/08 T-con with Ben and Nicholas at 3pm Salt Lake City Time]]

=Timeline/Progress=
# Cuda Integration into Slicer/CMake works (on Kubuntu)
# NH will write paper on IV-CUDA rendering for Journal
# Hata suggested publication of ITK-CUDA registration in Insight Journal (Feb)
# Benjamin will have short summery as of March 15 for MICCAI.
# Benjamin will finish his master by May 15th.

*Pointer to Google Notebook of the Work Progress of Ben: [http://www.google.com/notebook/public/08097279861700679221/BDQdBIgoQ1czeruoi?hl=en Notebook]
*Wiki page for [[ITK Image Registration with CUDA]]

=Misc notes=
#Link to [[Slicer3:Volume_Rendering]]
#[[Getting Cuda and CMake to run together]]
#Check out the [http://svn.orxonox.net/subprojects/volrenSample samplecode] for a Cuda and CMake project for Volume Rendering

== Cuda Examples ==
#[http://courses.ece.uiuc.edu/ece498/al1/Syllabus.html Cuda Lecture]

=Resources=
A list of interesting resources for building and using '''CUDA''' within Slicer and VTK:

# CUDA Main page: http://developer.nvidia.com/object/cuda.html
# CMake-Cuda: http://www.sci.utah.edu/~abe/FindCuda.html
# CUDA lecture by David Kirk @ Univ. of Illinois: http://courses.ece.uiuc.edu/ece498/al1/Syllabus.html
# Nice Siggraph Presentation on Volume Rendering [[media:SIGGRAPH-GPU.pdf]]
==Volume Rendering Techniques==
# [http://mist.suenaga.m.is.nagoya-u.ac.jp/document/group__volumerendering__group.html Nagoya Software MIP]
## Source: [http://www.na-mic.org/Wiki/images/f/ff/Volumerenderer.h.txt Volumerenderer.h]
# [http://osirix-viewer.com/ Osirix approach]

Slicer-IGT:GPU-IGT:01/09/08 T-con with Ben and Nicholas at 3pm Salt Lake City Time

2008-01-09T22:41:54Z

Nicky: /* Registration */

= Topics =
== Slicer Integration ==

===Cuda Support Classes===
#Implement the host access side such as allocate memory, delete and so forth in vtk-Classes
#Combining effort in:
##vtkCudaMemory
##vtkCudaAlgorithm
##vtkCuda
##vtkTexture

== CUDA algorithms ==
=== Volume Rendering ===
Important features:
#use '''Camera Coordinates''' and Projection Matrix instead of rotationMatrix
##Currently planar projection
#use '''Z-Buffer''' from previous render
##easy todo.
#'''Lighting Model''' use multiple lights
#'''Color gradients''' rather than 2 colors

===Volume Rendering CUDA module===
Move all the code from the cuda Code into a Support Classes

=== Registration ===
# some debuggings of registration CUDA codes
# start to work on itk classes:
## itkCudaResampleImageFilter
## itkCudaImageToImageMetric

==Misc==
===Build===
#CUDA on Cygwin: use the --ccbin flag to set the compiler bin directory. (failed for me)

= Results =

== CUDA COLOR ==
COlor Map for to write to cuda

= Resources =
#[[Slicer-IGT/GPU-IGT]]
#[[Volume Rendering With Cuda]]

Slicer-IGT:GPU-IGT:01/09/08 T-con with Ben and Nicholas at 3pm Salt Lake City Time

2008-01-09T22:41:34Z

Nicky: /* Registration */

= Topics =
== Slicer Integration ==

===Cuda Support Classes===
#Implement the host access side such as allocate memory, delete and so forth in vtk-Classes
#Combining effort in:
##vtkCudaMemory
##vtkCudaAlgorithm
##vtkCuda
##vtkTexture

== CUDA algorithms ==
=== Volume Rendering ===
Important features:
#use '''Camera Coordinates''' and Projection Matrix instead of rotationMatrix
##Currently planar projection
#use '''Z-Buffer''' from previous render
##easy todo.
#'''Lighting Model''' use multiple lights
#'''Color gradients''' rather than 2 colors

===Volume Rendering CUDA module===
Move all the code from the cuda Code into a Support Classes

=== Registration ===
# some debuggings of registration CUDA codes
# start to work on itk classes:
## itkResampleImageFilter
## itkImageToImageMetric

==Misc==
===Build===
#CUDA on Cygwin: use the --ccbin flag to set the compiler bin directory. (failed for me)

= Results =

== CUDA COLOR ==
COlor Map for to write to cuda

= Resources =
#[[Slicer-IGT/GPU-IGT]]
#[[Volume Rendering With Cuda]]

Slicer-IGT/GPU-IGT/112707

2007-12-06T14:23:07Z

Nicky:

# Introduction of members of this project
* Nicholas: student from Tokyo
* Benjamin: student from ETH, be at SPL for 6 mo. till May 31, 2007. Experience in golfing simulator, histoscopy simulator, open-source game software. His project here is GPU accelerated Slicer for 4D IGT.

# Nicholas update on his CUDA project
* Rigid and non-rigid registration using CUDA using Nvidia 8800 GTX (350GFlps) compatible with CUDA platform.
* Rigid registration (Japanese cas paper)
[[Image:RigidReg.jpg]]

Rigid registration using affine transformation, MI similarity measure, and Powell optimization method impletented on CUDA platform. GPU-acceleration was performed on affine transformation and MI similarity measure. Performance boost of around x12 was achieved.
* Non-rigid registration (also Japanese cas paper)
[[Image:NonrigidReg.jpg]]

Non-rigid registration using Rueckert's B-spline algorithm. Performance boost of around x10-x20 was achieved.

#Tool kit used
*CUDA calculator
*8800GTX, 8800GTS, Quadro FX5600, Tesla C870 is CUDA 1.0 compatible
*8600GTS, 8800GT is CUDA 1.1 compatible which comes with Atomic function to control cuncurrent access to memoery from multiple thread

# Extension to ITK
* CMake turn on/off #DEFINE
* VTK VolumePro as part of volume redering
* ITK parallelized process
* [Action items, Nichoals] Mid-term goal for Nicholas is to port his rigid and non-rigid regstration to ITK
* [Action items, Nicholas] Contact Utah team hear how exactly they implement their ITK.
* [Action items, Nicholas] sending volume rendering code by Dec. 6th.

# Volume rendering
* CUDA accelerated volume rendering
* x15 - 20 improvement
* comparison to other people's CG-based volume rendering [[media:SIGGRAPH-GPU.pdf]]
* [Action items, Benjamin] port CUDA-based volume rendering to vtk volume rendering classes, and then to Slicer
* [Action items, Benjamin] succeed Nicholas' itk-cuda-rigid non-rigid regstration and port them to Slicer in the context of MRg cardiac ablation

# Timeline
* NH will write paper on IV-CUDA rendering for Journal
* Hata suggested publication of ITK-CUDA registration in Insight Journal (Feb)
* Benjamin will have short summery as of March 15 for MICCAI.
* Benjamin will finish his project by May 15th.
* Benjamin
# Communication
Bi-weekly t-con to update each other week. Next one is Dec 11, 2007 at 9am.

File:NonrigidReg.jpg

2007-12-06T14:19:58Z

Nicky: Non-rigid registration processing flow. GPU- accelerated processes are marked with grey box.

Non-rigid registration processing flow. GPU- accelerated processes are marked with grey box.

Slicer-IGT/GPU-IGT/112707

2007-12-06T14:18:18Z

Nicky:

# Introduction of members of this project
* Nicholas: student from Tokyo
* Benjamin: student from ETH, be at SPL for 6 mo. till May 31, 2007. Experience in golfing simulator, histoscopy simulator, open-source game software. His project here is GPU accelerated Slicer for 4D IGT.

# Nicholas update on his CUDA project
* Rigid and non-rigid registration using CUDA using Nvidia 8800 GTX (350GFlps) compatible with CUDA platform.
* Rigid registration (Japanese cas paper)
[[Image:RigidReg.jpg]]

Rigid registration using affine transformation, MI similarity measure, and Powell optimization method impletented on CUDA platform. GPU-acceleration was performed on affine transformation and MI similarity measure. Performance boost of around x12 was achieved.
* Non-rigid registration based on (Rueckert et al.). achieved x10-x20

#Tool kit used
*CUDA calculator
*8800GTX is CUDA 1.0 compatible
* XXXX is CUDA 1.1 compatible which comes with Atomic function to control cuncurrent access to memoery from multiple thread

# Extension to ITK
* CMake turn on/off #DEFINE
* VTK VolumePro as part of volume redering
* ITK parallelized process
* [Action items, Nichoals] Mid-term goal for Nicholas is to port his rigid and non-rigid regstration to ITK
* [Action items, Nicholas] Contact Utah team hear how exactly they implement their ITK.
* [Action items, Nicholas] sending volume rendering code by Dec. 6th.

# Volume rendering
* CUDA accelerated volume rendering
* x15 - 20 improvement
* comparison to other people's CG-based volume rendering [[media:SIGGRAPH-GPU.pdf]]
* [Action items, Benjamin] port CUDA-based volume rendering to vtk volume rendering classes, and then to Slicer
* [Action items, Benjamin] succeed Nicholas' itk-cuda-rigid non-rigid regstration and port them to Slicer in the context of MRg cardiac ablation

# Timeline
* NH will write paper on IV-CUDA rendering for Journal
* Hata suggested publication of ITK-CUDA registration in Insight Journal (Feb)
* Benjamin will have short summery as of March 15 for MICCAI.
* Benjamin will finish his project by May 15th.
* Benjamin
# Communication
Bi-weekly t-con to update each other week. Next one is Dec 11, 2007 at 9am.

File:RigidReg.jpg

2007-12-06T14:14:02Z

Nicky: Rigid registration processing flow. GPU-accelerated processes are marked with grey box.

Rigid registration processing flow. GPU-accelerated processes are marked with grey box.

Slicer-IGT/GPU-IGT

2007-12-04T13:43:59Z

Nicky: /* Resources */

=Objective=
=Events=
=t-cons=
* [http://wiki.na-mic.org/Wiki/index.php/Slicer-IGT/GPU-IGT/112707 Nov 27, 2007]

=Progress=
=Misc notes=
=Resources=
A list of interesting resources for building and using '''CUDA''' within Slicer and VTK:

# CUDA Main page: http://developer.nvidia.com/object/cuda.html
# CMake-Cuda: http://www.sci.utah.edu/~abe/FindCuda.html
# CUDA lecture by David Kirk @ Univ. of Illinois: http://courses.ece.uiuc.edu/ece498/al1/Syllabus.html

==Volume Rendering Techniques==
# [http://mist.suenaga.m.is.nagoya-u.ac.jp/document/group__volumerendering__group.html Nagoya Software MTI]
# [http://osirix-viewer.com/ Osirix approach]

Slicer-IGT/GPU-IGT

2007-12-04T13:43:33Z

Nicky: /* Resources */

=Objective=
=Events=
=t-cons=
* [http://wiki.na-mic.org/Wiki/index.php/Slicer-IGT/GPU-IGT/112707 Nov 27, 2007]

=Progress=
=Misc notes=
=Resources=
A list of interesting resources for building and using '''CUDA''' within Slicer and VTK:

# CUDA Main page: http://developer.nvidia.com/object/cuda.html
# CMake-Cuda: http://www.sci.utah.edu/~abe/FindCuda.html
# CUDA lecture from David Kirk @ Univ. of Illinois: http://courses.ece.uiuc.edu/ece498/al1/Syllabus.html

==Volume Rendering Techniques==
# [http://mist.suenaga.m.is.nagoya-u.ac.jp/document/group__volumerendering__group.html Nagoya Software MTI]
# [http://osirix-viewer.com/ Osirix approach]

Slicer-IGT/GPU-IGT/112707

2007-12-04T13:19:38Z

Nicky:

# Introduction of members of this project
* Nicholas: student from Tokyo
* Benjamin: student from ETH, be at SPL for 6 mo. till May 31, 2007. Experience in golfing simulator, histoscopy simulator, open-source game software. His project here is GPU accelerated Slicer for 4D IGT.

# Nicholas update on his CUDA project
* Rigid and non-rigid registration using CUDA using Nvidia 8800 GTX (350GFlps) compatible with CUDA platform.
* Rigid registration (Japanese cas paper) *******to be filled by Nicholas ****** x12
* Non-rigid registration based on (Rueckert et al.). achieved x10-x20

#Tool kit used
*CUDA calculator
*8800GTX is CUDA 1.0 compatible
* XXXX is CUDA 1.1 compatible which comes with Atomic function to control cuncurrent access to memoery from multiple thread

# Extension to ITK
* CMake turn on/off #DEFINE
* VTK VolumePro as part of volume redering
* ITK parallelized process
* [Action items, Nichoals] Mid-term goal for Nicholas is to port his rigid and non-rigid regstration to ITK
* [Action items, Nicholas] Contact Utah team hear how exactly they implement their ITK.
* [Actoinj items, Nicholas] sending volume rendering code by Dec. 6th.

# Volume rendering
* CUDA accelerated volume rendering
* x15 - 20 improvement
* comparison to other people's CG-based volume rendering [[media:SIGGRAPH-GPU.pdf]]
* [Action items, Benjamin] port CUDA-based volume rendering to vtk volume rendering classes, and then to Slicer
* [Action items, Benjamin] succeed Nicholas' itk-cuda-rigid non-rigid regstration and port them to Slicer in the context of MRg cardiac ablation

# Timeline
* NH will write paper on IV-CUDA rendering for Journal
* Hata suggested publication of ITK-CUDA registration in Insight Journal (Feb)
* Benjamin will have short summery as of March 15 for MICCAI.
* Benjamin will finish his project by May 15th.
* Benjamin
# Communication
Bi-weekly t-con to update each other week. Next one is Dec 11, 2007 at 9am.

User:Nicky

2007-11-22T13:03:24Z

Nicky:

Nicholas Herlambang

Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Japan

[http://www.atre.t.u-tokyo.ac.jp/en/content/view/43/80/ go to my homepage..]

User:Nicky

2007-11-13T23:03:41Z

Nicky: New page: Nicholas Herlambang Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Japan

Nicholas Herlambang

Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Japan