2008 Summer Project Week:MRSegmentationWithoutAtlas
Key Investigators
- MIT: Tammy Riklin-Raviv, Polina Golland
Objective
Our objective is the simultaneous segmentation of N aligned MR images where the regions of interest are corresponding anatomical (brain) structures across N subjects. We assume that a probability atlas is not available.
Approach, Plan
We developed an EM approach for the simultaneous segmentation of N images while alternately estimating the probability map of the region of interest based on the segmentations obtained in the previous iteration.
In the project week we plan to test the algorithm developed on the UNC Autism MRI data.
Progress
We have implemented the algorithm and tested it on MRI images of 50 subjects.
References
T.F. Chan and L.A. Vese, "Active Contours Without Edges", Image Processing, vol. 10, pp. 266-277, 2001.
K. Van Leemput and F. Maes and D. Vandermeulen and P. Suetens, "Automated model-based tissue classification of {MR} images of the brain", IEEE transactions on medical imaging, vol. 18, no. 10, pp. 897-908, 1999.