Some Applications of GPU-Based Medical Imaging

1
Some Applications of GPU-Based Medical Imaging

• Baohua Wu

2
Roadmap

• Introduction
• Medical imaging applications
• Decompression
• Registration
• Conclusion

3
Introduction to GPU-based Medical Imaging

• Visualization
• Segmentation
• Registration
• Codec
• Source Gianluca Paladini, State of the Art in
  GPU-Accelerated Techniques for Medical Imaging,
  GTC09

4
Motivations

• Challenges from medical imaging
• Large volume of data (gigabytes to terabytes)
• Processing time on CPU (minutes, hours or even
  days)
• Limitations of some hardware
• parallel computers
• FPGA, dedicated devices
• GPUs emergence offers a solution

5
Visualization of Medical Images

• Automatic carving
• 4D flow visualization
• Diffusion tractography
• Virtual endoscopy (ex. artery)
• Virtual unfolding (ex. colon)
• Tissue classification
• Virtual mirrors
• etc

6
Image Segmentation

• Segmentation refers to the process of
  partitioning a digital image into multiple
  segments wikipedia.org

Source Gianluca Paladini, State of the Art in
GPU-Accelerated Techniques for Medical Imaging,
GTC09
7
Image Registration
Source http//www.siam.org/meetings/op08/Modersit
zki.pdf
8
GPU-Accelerated Registration

• Adaptive Radiation Therapy
• Real-time ultrasound / CT registration

9
Application 1

• GPU-based Decompression for Medical Imaging
  Applications
• Albert Wegener
• GPU Technology Conference 2009

10
Faster Imaging System
11
(No Transcript)
12
Problems Solutions

• Serial coding with VLC (Variable Length Code)
• Data are stored in packets that can be decoded in
  parallel
• Small shared memory prevents storing one entire
  packet per thread
• n symbols at a time
• Conditionals lead to divergent warps
• Replace conditionals with lookup tables

13
Data-driven look-up table
14
Application 2

• Medical Image Registration with CUDA
• Richard Ansorge
• GTC 09

15
Method

• Deformation model
• Affine
• B-spline
• Search strategy
• Simplex
• Gradient descent
• Cost function
• correlation coefficient
• mutual information

16
(No Transcript)
17
(No Transcript)
18
(No Transcript)
19
2D histogram of intensities of two images

• Source F. E. M. S. Matthias Tessmann, Christian
  Eisenacher and P. Hastreiter. Gpu accelerated
  normalized mutual information and b-spline
  transformation. In Eurographics Workshop on
  Visual Computing for Biomedicine (EG VCBM), pages
  117124, 2008.

20
(No Transcript)
21
(No Transcript)
22
(No Transcript)
23
Application 3

• Fast deformable registration on the gpu A cuda
  implementation of demons
• P. Muyan-Ozcelik, J. Owens, J. Xia, and S. Samant
• IEEE Conference on Computational Sciences andIts
  Applications, 2008

24
Demons Algorithm
Source J.-P. Thirion, Image matching as a
diffusion process an analogy with Maxwells
Demons, MIA 98
25
Demons Algorithm

• v the displacement
• where S the static image, M the moving image,
  i a position in the image
• Similarity measure of Correlation Coefficient
• where D the deformed moving image

26
Control flow graphof Demons algorithm

• Source X. Gu, H. Pan, Y. Liang, R. Castillo, D.
  Yang, D. Choi, E. Castillo, A. Majumdar, T.
  Guerrero, and S. B. Jiang. Implementation and
  evaluation of various demons deformable image
  registration algorithms on a gpu. Physics in
  Medicine and Biology, 55(1)207-219, 2010.

27
CUDA Kernels
28
Speedups
29
Conclusion

• GPU opens the prelude of a new era for medical
  imaging
• Post-processing to real-time processing with
  speedups from tens to hundreds of times
• More automated workflow in surgical operations
• Interventional medical imaging
• Adaptive radiation therapies

30
Acknowledgement

• Joseph T Kider Jr.
• Jonathan McCaffrey
• Gang Song
• Dr. Brian Avants
• Dr. James Gee