Deformable Atlas for Multi-structure Segmentation

Xiaofeng Liu, Albert Montillo, Ek.T. Tan, John F. Schenck, and Paulo Mendonca

Abstract. We develop a novel deformable atlas method for multi-structure segmentation that seamlessly combines the advantages of image-based and atlas-based methods. The method formulates a probabilistic framework that combines prior anatomical knowledge with image-based cues that are specific to the subject’s anatomy, and solves it using expectation-maximization method. It improves the segmentation over conventional label fusion methods especially around the structure boundaries, and is robust to large anatomical variation. The proposed method was applied to segment multiple structures in both normal and diseased brains and was shown to significantly improve results especially in diseased brains.

Keywords: Segmentation, deformable atlas, label fusion, MLE, GVF

LNCS 8149, p. 743 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2013