TOADS: topology-preserving, anatomy-driven segmentation

This paper presents a new framework for multiple object segmentation in medical images that respects the topological properties and anatomical relationships of structures as given by a template. The technique, known as TOADS (TOpology-preserving, Anatomy-driven Segmentation), combines advantages of statistical tissue classification, topology-preserving fast marching, and image registration to enforce object-level relationships with little constraint over the geometry. When applied to the problem of brain segmentation, it directly provides a cortical surface with spherical topology while segmenting the main cerebral structures. Validation on simulated and real images characterize the performance of the algorithm with regard to noise, inhomogeneities, and anatomical variations.

• Type: Conference
• Year: 2006
• Where: ISBI
• Authors: Pierre-Louis Bazin, Dzung L. Pham
• Keywords: Anatomy-driven Segmentation, ISBI 2006, Medical Imaging, Multiple Object Segmentation, Topology-preserving Fast Marching