A Region of Interest Approach

1
A Region of Interest Approach For Medical Image
Compression

• Salih Burak Gokturk
• Stanford University

2
OVERVIEW

• Motivation
• Previous Work
• Comparison Study of Compression Schemes
• ROI based System Design
• Conclusion

3
Motivation

• Medical images are huge.(300x512x512x2)
• High quality imaging is required in
  diagnostically important regions.
• ROI based approach is the only solution
• Lossless compression in ROI.
• Very lossy compression in non-ROI.

4
OVERVIEW

• Motivation
• Previous Work
• Comparison Study of Compression Schemes
• ROI based System Design
• Conclusion

5
Previous Work

• Lossless Compression Schemes (Takaya95, Assche00)
• DCT based Compression Schemes (Vlaciu95)
• PCA based Compression(Tao96)
• Wavelet Transformation(2D and 3D) (Baskurt93)
• ROI based coding (Cosman 94,95)

6
OVERVIEW

• Motivation
• Previous Work
• Comparison Study of Compression Schemes
• ROI based System Design
• Conclusion

7
Lossless Compression

• Entropy of images 7.93bpp
• Predictive Coding 5.9bpp
• Entropy of difference images 5.76bpp

8
DCT Compression (1)
9
DCT Compression (2)
10
DCT Compression (3)
11
PCA Compression
- Treat each image block as a vector
Rate 0.54 bpp
MSE 30 dB
12
Blockwise Vector Quantization(1)
- A simpler decoder is required
13
Blockwise Vector Quantization(2)
MSE 39 dB
MSE 38 dB
14
Motion Compensated Hybrid Coding (1)
- Lukas Kanade Tracker was used by 0.1 pixel
accuracy
15
Lukas-Kanade Tracker
16
Motion Compensated Hybrid Coding (2)

• Entropy of the motion vector is 2.28 and 2.45 in
  x and y.
• This brings 0.018 bpp.

MSE 35 dB
17
OVERVIEW

• Motivation
• Previous Work
• Comparison Study of Compression Schemes
• ROI based System Design
• Conclusion

18
Segmentation

• Thresholding to find the air
• Gradient magnitude to extract the colon wall
• Grassfire operation to find the ROI around the
  colon wall

19
ROI Based System
20
Experiment with 16 by 16 Blocks

• The ratio of ROI 12.2
• Entropy of motion vector is 2.28 in x and 2.45
  in y
• The entropy of the error image is 4.38
• average RMS error 33.7 dB with lossless in ROI
• Overall rate 0.552 bps

MSE 33.7 dB
21
Experiment with 8 by 8 Blocks

• The ratio of ROI 7.3
• Entropy of motion vector is 1.82 in x and 1.96
  in y
• The entropy of the error image is 4.31
• average RMS error 30.3 dB with lossless in ROI
• Overall rate 0.37 bps

MSE 30.3 dB
MSE 33.7 dB
22
OVERVIEW

• Motivation
• Previous Work
• Comparison Study of Compression Schemes
• ROI based System Design
• Conclusion

23
Conclusion

• Effective System (compression rate of 2.3)
• Accurate System (lossless in ROI)
• Results of ROI based compression over performs
  standard compression schemes.
• Future work includes lossy compression in ROI.
• Case study with the radiologist for determining
  rate-diagnosis performance curve.