AUTOMATED BRAIN SEGMENTATION FROM SINGLE SLICE, MULTISLICE, OR WHOLE-VOLUME MR SCANS USING PRIOR KNOWLEDGE

Purpose: An automated procedure has been developed to isolate the brai n in single/multislice or whole-volume MR images obtained from various sequences. Method: T1-weighted, T2-weighted, and inversion recovery i mages were acquired. The brain segmentation procedure employed (A) a k nowledge base that held generic information about the brain in the thr ee orthogonal views and (B) a texture definition and intensity charact eristics of features within the head. The brain was segmented by selec tively blurring scans using components of B; contour following with re gion growing was initiated until the isolated feature satisfied the me asurements in A. Results: The brain was segmented automatically from 2 10 subjects (whale volume) and 52 subjects (multi/single slice). Detai led analysis of seven segmented brains showed that <0.8% of the contou r pixels were erroneously identified. Whole-volume head scans consisti ng of 140 x 256 x 256 pixels were segmented in <30 min. Conclusion: A robust, fast, and efficient procedure has been developed to segment th e brain from MR images.