Deformable atlas for multi-structure segmentation.

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

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


We develop a novel deformable atlas method for multistructure 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.

Original languageEnglish (US)
Pages (from-to)743-750
Number of pages8
JournalMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Issue numberPt 1
StatePublished - Dec 1 2013

ASJC Scopus subject areas

  • Medicine(all)


Dive into the research topics of 'Deformable atlas for multi-structure segmentation.'. Together they form a unique fingerprint.

Cite this