Selective Invocation of Shape Priors for Deformable Segmentation and Morphologic Classification of Prostate Cancer Tissue Microarrays

Active Contours (AC) can be categorized as boundary-based (first generation) and region-based (second generation) schemes [20,3,5]. Most AC models are not intrinsically capable of handling object occlusion or scene clutter. Therefore, the integration of shape priors into the variational formulation represents a natural way to overcome occlusion. Third generation (hybrid) AC models involve combining a shape prior with geometric/geodesic active contours that simultaneously achieves registration and segmentation [21,26,4].

Source: Computerized Medical Imaging and Graphics - November 11, 2014 Category: Radiology Authors: Sahirzeeshan Ali, Robert Veltri, Jonathan A. Epstein, Christhunesa Christudass, Anant Madabhushi Source Type: research