Home
Registration
Super-Resolution
Bacteria Identification
Doppler analysis
MSL segmentation
CGMM
X-ray classification
Cervigrams
Image Clustering
Video Indexing
Object tracking
Gmm&Edge

Statistical Space-Time Segmentation
of Active Multiple Sclerosis Lesions

Overview

The objective of the proposed statistical modeling scheme is to automatically detect, segment and track-in-time regions pertaining to relapsing-remitting multiple sclerosis (MS) lesions in MR image-sequences of the brain. Unsupervised clustering via Gaussian mixture modeling is utilized to extract coherent space-time regions (space-time “blobs”) in a four-dimensional feature space (intensity, position (x,y), and time) and corresponding coherent segments in the sequence content. The parameters of the model are determined via the Expectation-Maximization (EM) algorithm according to the maximum likelihood principle. In the detection stage of the framework, the regions corresponding to MS lesions are identified out of the collection of extracted segments based on region-level rules. Following the detection, lesion segmentation and tracking are performed in a unified manner via global space-time modeling.

The performance of the proposed framework was demonstrated using a well-known benchmark sequence of 24 MR images, acquired from a relapsing-remitting MS patient over a period of approximately a year. Strong correlation was achieved between the automatically obtained segmentation results and an expert’s manual segmentation. Robustness tests via a simulation tool further confirmed the validity of the suggested methodology.

Examples of Lesion Segmentation and Tracking in Time


Original sequence (frames 1,3,8,20)


Space-time segmentation of lesions; each active lesion is marked by a different color.
Static lesions and non-lesion regions are in black.

For a detailed explanation read the Thesis.

Publications

bullet

A. Shahar and H. Greenspan, “Probabilistic Spatial-Temporal Segmentation of Multiple Sclerosis Lesions,” in Proceedings to the Computer Vision Approaches to Medical Image Analysis Workshop  (CVAMIA), Prague, May 2004, to be published. [pdf]

bullet

A. Shahar and H. Greenspan, “A Probabilistic Framework for the Detection and Tracking in Time of Multiple Sclerosis Lesions,” in Proceedings to the IEEE Symposium on Biomedical Imaging, Arlington, VA, Apr. 2004, to be published. [pdf]

bullet

H. Greenspan, A. Mayer, and A. Shahar, “A Probabilistic Framework for the Spatio-Temporal Segmentation of Multiple Sclerosis Lesions in MR Images of the Brain,” in Proceedings of SPIE International Symposium on Medical Imaging, San Diego, CA, pp. 1551-1559, Feb. 2003. [ps]

 

horizontal rule

Home Registration Super-Resolution Bacteria Identification Doppler analysis MSL segmentation CGMM X-ray classification Cervigrams Image Clustering Video Indexing Object tracking Gmm&Edge

For problems or questions regarding this web page contact hayit@eng.tau.ac.il.
Last updated: 01/07/08.