Abstract #1605

Huang A, Abugharbieh R, Tam R, Traboulsee A

We present a novel automatic 3D segmentation method for extracting brain cortex from T1-weighted MRI scans and segmenting gray and white matter by incorporating a statistical as well as a geometric model in a unified segmentation scheme. Combined with the expectation maximization algorithm, and both voxel probability and image gradient and curvature information, geodesic active contours are evolved to segment the cortex and brain tissues. The robustness and accuracy of our proposed method are validated with both synthetic and real data. Both quantitative and qualitative results indicate superior and consistent performance when compared with standard techniques including SPM and FSL.