TOADS: Topology-Preserving, Anatomy-Driven Segmentation
Pierre‐Louis Bazin, Dzung L. Pham · 2006
This paper presents a new algorithm for object segmentation in medical images that respects the topological properties and anatomical relationships of structures as given by a template. The technique combines advantages of tissue classification, digital topology, and image registration to handle any given topology and enforces object-level relationships with little constraint over the geometry. It is applied to cortical segmentation and validated on simulated and real images