Seminar in Medical Image Segmentation
CSE 702, University at Buffalo SUNY
Syllabus for Fall 2007
Last updated: 10 Sept 2007


Instructor:
Jason Corso (jcorso@cse)

Course Webpage:

http://www.cse.buffalo.edu/~jcorso/t/2007fall_smis.
Syllabus in pdf: http://www.cse.buffalo.edu/~jcorso/t/2007fall_smis/syllabus.pdf.
Downloadable course material can be found on the UBLearns site.

Course Overview:

The seminar will survey the recent literature in medical image segmentation. We treat the definition of segmentation loosely and include the related problems of detection, segmentation, and labeling. Topics include knowledge-based heuristics, voxel-based statistical classification, deformable models and level-sets, hierarchical modeling, medial-axis shape representations, graph-cuts, and learning-based approaches. We will focus on constructing a complete taxonomy of approaches in this area. Students will be required to make one paper presentation and do a project to explore a method, which can be new research, in detail. Familiarity with vision and medical image computing is suggested but not required.

Course Goals:

  1. Breadth Goal: Each student will gain an understanding of the breadth of methods used in medical image segmentation.
  2. Depth Goal: Each student will gain a detailed understanding of one particular approach.

Textbooks:
Required material distributed by instructor or found on the UB Libraries electronical journal archive.

Meeting Times:
Time is Wednesday at 3:30-6PM.

Location:
Bell Hall 224

Office Hours:
T1-3 and R1-2

Grading:
Letter grading distributed as follows:

Programming Language:
Depends on student chosen project (generally, C++).

Calendar

  Week Topics and Readings Presenter
1 8/29


Introduction. Definition of problems and difficulties in medical image segmentation.

 

2

 9/5


Discussion of proposed taxonomy and review of some classical approaches.
Primary Readings: [Bezdek et al., 1993,Pham et al., 2000]
Secondary Readings: [Van Ginneken et al., 2001,McInerney et al., 1996,Clarke et al., 1995,Noble & Boukerroui, 2006,Engle Jr., 1992]



Part I: Paper Reading and Presentations
Each week one student is responsible for preparing a 30 minute talk on the primary paper for that week. The class-time is split up into three parts. For the first 45 minutes, the instructor will give background material to the class and lead the discussion during which the class will define a set of questions to ask the presenter. During this time, the presenter for the week is not present. Following this initial discussion, the presenter will give his or her talk (30 minutes). For the remaining time (roughly an hour), the class will query the presenter with the prepared questions followed by a general discussion. (This process follows the Study Groups at the IPMI conference.)
3 9/12


Statistical Classification via Expectation-Maximization
Primary Reading: [Leemput et al., 2003]
Secondary Readings: [Dempster et al., 1977,Dellaert, 2002]

V. Singh
4 9/19


Statistical Classification in a Hierarchical Model
Primary Reading: [Blekas et al., 2005,Pohl et al., 2007]
Secondary Readings: [Dempster et al., 1977,Dellaert, 2002]

C. Hoeflich (Blekas)
C. Kao (Pohl)
5 9/26


Markov Random Fields Modeling for Medical Image Segmentation
Primary Readings: [Held et al., 1997]
Secondary Readings: [Winkler, 1995, Ch. 3] [Zhang et al., 2001,Rajapakse et al., 1997]

R. Alomari
6 10/3


Graph-Shifts Segmentation: Dynamic Hierarchical Energy Minimization
Primary Readings: [Corso et al., 2007b,Corso et al., 2007a]
Secondary Readings: [Lafferty et al., 2001,Kumar & Hebert, 2003,Tu, 2005]

A. Chen
7 10/10


Bayesian Segmentation by Weighted Aggregation
Primary Readings: [Corso et al., n.d.,Akselrod-Ballin et al., 2006]
Secondary Readings: [Corso et al., 2006,Sharon et al., 2000,Sharon et al., 2001]

I. Nwogu
8 10/17


Hybrid Generative-Discriminative Models and 3D Region Competition
Primary Readings: [Tu et al., 2007]
Secondary Readings: [Zhu & Yuille, 1996,Tu, 2005]

M. Yaqub
9 10/24


Minimum Description Length Active Shape Models
Primary Readings: [Heimann et al., 2005]
Secondary Readings: [Cootes et al., 1995,Cootes et al., 2001,Davies et al., 2002]

P. Noel
10 10/31


Class Cancelled For MICCAI 2007


11 11/7


Deformable Medial-Axis Shape-Based Segmentation
Primary Readings: [Pizer et al., 2003]
Secondary Readings: [Joshi et al., 2001,McInerney et al., 1996]

J. Evanko
12 11/14


Shape Regression Machine and Image-Based Regression
Primary Readings: [Zhou & Comaniciu, 2007]
Secondary Readings: [Zhou et al., 2005,Viola & Jones, 2001,Freund & Schapire, 1997]

R. Rodrigues


Part II: Project Presentations
Each student doing a project will give a 20-minute conference style presentation of the work.
13 11/21


Class Cancelled for Thanksgiving Holiday


14 11/28




 
15 12/5




 

Bibliography

Akselrod-Ballin et al., 2006
Akselrod-Ballin, A., Galun, M., Gomori, M. J., Filippi, M., Valsasina, P., Basri, R., & Brandt, A. 2006.
Integrated Segmentation and Classification Approach Applied to Multiple Sclerosis Analysis.
In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

Bezdek et al., 1993
Bezdek, J.C., Hall, L.O., & Clarke, L.P. 1993.
Review of MR Image Segmentation Techniques Using Pattern Recognition.
Medical Physics, 20(4), 1033-1048.

Blekas et al., 2005
Blekas, K., Galatsanos, N. P., Likas, A., & Lagaris, I. E. 2005.
Mixture model analysis of DNA microarray images.
Medical Imaging, IEEE Transactions on, 24(7), 901-909.

Clarke et al., 1995
Clarke, L. P., Velthuizen, R. P., Camacho, M. A., Heine, J. J., Vaidyanathan, M., Hall, L. O., Thatcher, R. W., & Silbiger, M. L. 1995.
MRI Segmentation: Methods and Applications.
Magnetic Resonance Imaging, 13(3), 343-368.

Cootes et al., 1995
Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. 1995.
Active shape models-their training and application.
Comput. Vis. Image Underst., 61(1), 38-59.

Cootes et al., 2001
Cootes, T.F., Edwards, G.J., & Taylor, C.J. 2001.
Active appearance models.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6), 681-685.

Corso et al., n.d.
Corso, J. J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., & Yuille, A.
Efficient Multilevel Brain Tumor Segmentation with Integrated Bayesian Model Classification.
IEEE Transactions on Medical Imaging.
(in press).

Corso et al., 2006
Corso, J. J., Sharon, E., & Yuille, A. 2006.
Multilevel Segmentation and Integrated Bayesian Model Classification with an Application to Brain Tumor Segmentation.
Pages 790-798 of: Medical Image Computing and Computer Assisted Intervention, vol. 2.

Corso et al., 2007a
Corso, J. J., Yuille, A. L., Sicotte, N. L., & Toga, A. W. 2007a.
Detection and Segmentation of Pathological Structures by the Extended Graph-Shifts Algorithm.
In: Proceedings of Medical Image Computing and Computer Aided Intervention (MICCAI).

Corso et al., 2007b
Corso, J. J., Tu, Z., Yuille, A., & Toga, A. W. 2007b.
Segmentation of Sub-Cortical Structures by the Graph-Shifts Algorithm.
Pages 183-197 of: Karssemeijer, N., & Lelieveldt, B. (eds), Proceedings of Information Processing in Medical Imaging.

Davies et al., 2002
Davies, R. H., Twining, C. J., Cootes, T.F., Waterton, J. C., & Taylor, C.J. 2002.
A Minimum Description Length Approach to Statistical Shape Modeling.
IEEE Transactions on Medical Imaging, 21(5), 525-537.

Dellaert, 2002
Dellaert, F. 2002.
The Expectation Maximization Algorithm.
Tech. rept. 20. Georgia Institute of Technology.

Dempster et al., 1977
Dempster, A. P., Laird, N. M., & Rubin, D. B. 1977.
Maximum Likelihood From Incomplete Data via the EM Algorithm.
Journal of the Royal Statistical Society - Series B, 39(1), 1-38.

Engle Jr., 1992
Engle Jr., R. 1992.
Attempts to User Computers as Diagnostic Aids in Medical Decision Making: A Thirty-Year Experience.
Perspectives in Biology and Medicine, 35, 207-219.

Freund & Schapire, 1997
Freund, Y., & Schapire, R. E. 1997.
A Decision-Theoretic Generalization of On-line Learning and an Application to Boosting.
Journal of Computer and System Science, 55(1), 119-139.

Heimann et al., 2005
Heimann, T., Wolf, I., Williams, T. G., & Meinzer, H.-P. 2005.
3D Active Shape Models Using Gradient Descent Optimization of Description Length.
Pages 566-577 of: Proceedings of Information Processing in Medical Imaging.

Held et al., 1997
Held, K., Kops, E. R., Krause, B. J., Wells, W. M., III., Kikinis, R., & Muller-Gartner, H. W. 1997.
Markov random field segmentation of brain MR images.
Medical Imaging, IEEE Transactions on, 16(6), 878-886.

Joshi et al., 2001
Joshi, S., Pizer, S. M., Fletcher, P. T., Thall, A., & Tracton, G. 2001.
Multi-scale 3D Deformable Model Segmentation Based on Medical Description.
Pages 64-77 of: Information Processing in Medical Imaging (IPMI 2001).

Kumar & Hebert, 2003
Kumar, S., & Hebert, M. 2003.
Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification.
In: International Conference on Computer Vision.

Lafferty et al., 2001
Lafferty, J., McCallum, A., & Pereira, F. 2001.
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data.
In: Proceedings of International Conference on Machine Learning.

Leemput et al., 2003
Leemput, K. Van, Maes, F., Vandermeulen, D., & Suetens, P. 2003.
A Unifying Framework for Partial Volume Segmentation of Brain MR Images.
IEEE Transactions on Medical Imaging, 22(1), 105-119.

McInerney et al., 1996
McInerney, T., , & Terzopoulos, D. 1996.
Deformable Models in Medical Image Analysis: A Survey.
Medical Image Analysis, 1(2), 91-108.

Noble & Boukerroui, 2006
Noble, J. A., & Boukerroui, D. 2006.
Ultrasound Image Segmentation: A Survey.
Medical Imaging, IEEE Transactions on, 25(8), 987-1010.

Pham et al., 2000
Pham, D. L., Xu, C., & Prince, J. L. 2000.
Current Methods in Medical Image Segmentation.
Annual Review of Biomedical Engineering, 2, 315-337.

Pizer et al., 2003
Pizer, S. M., Fletcher, P. T., Joshi, S., Thall, A., Chen, J. Z., Fridman, Y., Fritsch, D. S., Gashi, A. G., Glotzer, J. M., Jiroutek, M. R., Lu, C., Muller, K. E., Tracton, G., Yushkevich, P., & Chaney, E. L. 2003.
Deformable M-Reps for 3D Medical Image Segmentation.
International Journal of Computer Vision, 55, 85-106.

Pohl et al., 2007
Pohl, K. M., Bouix, S., Nakamura, M., Rohlfing, T., McCarley, R. W., Kikinis, R., Grimson, W. E. L., Shenton, M. E., & Wells, W. M. 2007.
A Hierarchical Algorithm for MR Brain Image Parcellation.
IEEE Transactions on Medical Imaging, Special Issue on Mathematical Modeling in Biomedical Image Analysis.

Rajapakse et al., 1997
Rajapakse, J. C., Giedd, J. N., & Rapoport, J. L. 1997.
Statistical Approach to Segmentation of Single-Channel Cerebral MR Images.
Medical Imaging, IEEE Transactions on, 16(2), 176-186.

Sharon et al., 2000
Sharon, E., Brandt, A., & Basri, R. 2000.
Fast Multiscale Image Segmentation.
Pages 70-77 of: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. I.

Sharon et al., 2001
Sharon, E., Brandt, A., & Basri, R. 2001.
Segmentation and Boundary Detection Using Multiscale Intensity Measurements.
Pages 469-476 of: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. I.

Tu, 2005
Tu, Z. 2005.
Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering.
In: Proceedings of International Conference on Computer Vision.

Tu et al., 2007
Tu, Z., Narr, K. L., Dinov, I., Dollar, P., Thompson, P. M., & Toga, A. W. 2007.
Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models.
IEEE Transactions on Medical Imaging.
(in press).

Van Ginneken et al., 2001
Van Ginneken, B., Ter Haar Romeny, B. M., & Viergever, M. A. 2001.
Computer-Aided Diagnosis in Chest Radiography: A Survey.
Medical Imaging, IEEE Transactions on, 20(12), 1228-1241.

Viola & Jones, 2001
Viola, P., & Jones, M. 2001.
Rapid Object Detection using a Boosted Cascade of Simple Features.
In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

Winkler, 1995
Winkler, G. 1995.
Image Analysis, Random Fields and Dynamic Monte Carlo Methods.
Springer.

Zhang et al., 2001
Zhang, Y., Brady, M., & Smith, S. 2001.
Segmentation of Brain MR Images Through a Hidden Markov Random Field Model and the Expectation-Maximization Algorithm.
IEEE Transactions on Medical Imaging, 20(1), 45-57.

Zhou et al., 2005
Zhou, S., Georgescu, B., Zhou, X. Sean, & Comaniciu, D. 2005.
Image based Regression Using Boosting Method.
In: Proceedings of International Conference on Computer Vision.

Zhou & Comaniciu, 2007
Zhou, S. K., & Comaniciu, D. 2007.
Shape Regression Machine.
Pages 13-25 of: Karssemeijer, N., & Lelieveldt, B. (eds), Proceedings of Information Processing in Medical Imaging.

Zhu & Yuille, 1996
Zhu, S. C., & Yuille, A. 1996.
Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(9), 884-900.

About this document ...

Seminar in Medical Image Segmentation
CSE 702, University at Buffalo SUNY
Syllabus for Fall 2007
Last updated: 10 Sept 2007

This document was generated using the LaTeX2HTML translator Version 2002-2-1 (1.71)

Copyright © 1993, 1994, 1995, 1996, Nikos Drakos, Computer Based Learning Unit, University of Leeds.
Copyright © 1997, 1998, 1999, Ross Moore, Mathematics Department, Macquarie University, Sydney.

The command line arguments were:
latex2html -split 0 -nonavigation syllabus.tex

The translation was initiated by Jason Corso on 2007-09-10

Jason Corso 2007-09-10