Transcript Automatic Location detection navigation system

Tissue Image Segmentation
- Presenter : Lin Yang
- Advisor : Dr. David J. Foran
- “A General Framework for Segmenting Imaged
Pathology Specimens Using Level-set and
Gaussian Hidden Markov Random Fields ”
Problem Statement
 Image Segmentation

Region based method
• Segmentation by clustering – mean shift
• Segmentation by graph theory
• Segmentation by MRFs, Gaussian Mixture Models
and EM algorithm

Contour based method
• Active contour models
–
–
–
–
–
Traditional KWT snake
GVF snake
Geodesic snake
Level – set based snake
Active contour without edge
The Choice of Filter Bank(1)
 The Gabor filter bank
 The Leung – Malik (LM) filter bank
The Choice of Filter Bank(2)
 The Schmid filter bank
 The Maximum Response (MR) filter bank
MRF Segmentation Model
 Assume a set of observed (y) and hidden
(x) random variables
 fy represents the low-level features
 ωx represents the labels of each pixel
 Now the segmentation problem can be
modeled as a MAP(maximum a posterior)
estimation

Gibbs prior
 Gibbs prior
 Intuitive Understanding
 Hammersley-Clifford theorem
Gaussian Mixture Model
 Given feature f, the Gaussian Mixture
Model is defined as follows:
Initialization and EM
 Applying EM algorithm to get the MLE
estimation of the parameters set W:
Complete Cost Function
 The complete cost function combining the
Gaussian mixture models and the Gibbs
priors will have the following forms
 Notice that the parameters are the results
of EM algorithm
Optimization Algorithm (1)
 Stochastic optimization

Simulate Annealing
• Gibbs Sampling
• Global Minimum

Algorithm
• Code from Matlab
Optimization Algorithm (2)
Experimental Results(1)
 Synthetic Image
Experimental Results(2)
 Standard Texture Image
Level Set Based Active Contour
 Traditional Snake


Topological change
Difficulty with initialization problem – GVF snake
partially solve this problem
 Level – Set or Geodesic Snake

Topology changes can be easily handled and initial
positions are not sensitive
 Computation is complex, speed is slow and the
implementation is relatively difficult
 Multiphase level-set framework – very fast
 Snake with MRF

Apply snake on the likelihood map of MRF can mix
the advantages of MRF and snake
Experimental Results(3)
Experimental Results(4)
Performance Evaluation
 Features are more important than classification
algorithm

Deformable Model
• None of the gradient based or even region based deformable model
alone works well in our real case
 Gaussian Mixture Model
• The result is not very good because it will over-segment the image
• MRF based GMM will improve the result because the introduction of
Gibbs prior
 Clustering Based Segmentation
• Actually provide satisfactory results for texture only segmentation
• Has some problem with homogenous segmentation when combined
with intensity information
• Total unsupervised approach is very hard for our application
Pros and Cons
 Advantages:



Actually perform very well for our application.
Can be combined with many different segmentation
models
Still active field and even show up in CVPR 2005.
 Disadvantages:

Speed, speed and speed
• Hundreds of, if not thousands of, literatures are proposed for
increasing the speed.
• Matlab implementation and C/C++ implementation, big
difference, the C++ implementation takes only no more than
1 minute for one image with 600*600 pixels

Gaussian Models are not always, if not never, hold for
many medical image processing applications
Reference
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
Chad Carson, Serge Belongie, Hayit Greenspan and Jitendra Malik, “Blobworld: Image Segmentation
Using Expectation-Maximization and Its Application to Image Querying, ” IEEE Tran. on Pattern Anal.
and Mach. Intell., vol 24, no. 8, pp1027-1037
C. Bouman and B. Liu, “Multiple Resolution Segmentation of Textured Images,'' IEEE Trans. on Pattern
Anal. and Mach. Intell., vol. 13, no. 2, pp. 99-113, Feb. 1991.
C. A. Bouman and M. Shapiro, “A Multiscale Random Field Model for Bayesian Image
Segmentation,'' IEEE Trans. on Image Processing, vol. 3, no. 2, pp. 162-177, March 1994
R. O. Duda, P. E. Hart, and D. G. Stork, Patten Classification, 2nd Edition, Wiley, 2000.
David A. Forsyth and Jean Ponce, Computer Vision A Modern Approach, 1st Edition, Prentice Hall, 2003.
Mario A. T. Figueiredo, “Bayesian Image Segmentation Using Wavelet-Based Priors,” CVPR, vol. 1 pp
437-443, 2005.
R. Malladi, J. A. Sethian, B. C. Vemuri, "Shape Modeling with Front Propagation: A Level Set Approach,"
IEEE Trans. on Pattern Anal. and Mach. Intell., vol. 17 No. 2: 158-175, Feburary 1995.
T. F. Chan, L. A. Vese, "A Level Set Algorithm for Minimizing the Mumford-Shah Functional in Image
Processing," Proceedings of the IEEE Workshop on Variational and Level Set Methods, pp. 161-171,
2001.
Y. Zhang, M. Brady, S. Smith, “Segmentation of brain MR images through a hidden Markov random field
model and the expectation-maximization algorithm,” IEEE Transactions on Medical Imaging, Vol. 20, no
1, pp. 45 – 57, Jan 2001
T. Leung and J. Malik, “Representing and recognizing the visual appearance of materials using threedimensional textons,” International Journal of Computer Vision, 43(1):29-44, June 2001
Thank You