PATCH-DRIVEN NEONATAL BRAIN MRI SEGMENTATION WITH SPARSE REPRESENTATION AND LEVEL SETS

Neonatal brain MR image segmentation is challenging due to the poor image quality. In this paper, we propose a novel patch-driven level sets method for segmentation of neonatal brain images by taking advantage of sparse representation techniques. Specifically, we first build a subject-specific atlas from a library of aligned, manually segmented images by using sparse representation in a patch-based fashion. Then, the spatial consistency in the subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, this subject-specific atlas is integrated into a coupled level set framework for surface-based neonatal brain segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and on 132 additional testing subjects. Both quantitative and qualitative evaluation results demonstrate the validity of the proposed method.