#81: Clustering initiated multiphase active contours and robust separation of nuclei groups for tissue segmentation


Computer assisted or automated histological grad- ing of tissue biopsies for clinical cancer care is a long- studied but challenging problem. It requires sophis- ticated algorithms for image segmentation, tissue ar- chitecture characterization, global texture feature ex- traction, and high-dimensional clustering and classi- fication algorithms. Currently there are no automatic image-based grading systems for quantitative pathol- ogy of cancer tissues. We describe a novel approach for tissue segmentation using fuzzy spatial clustering, vector-based multiphase level set active contours and nuclei detection using an iterative kernel voting scheme that is robust even in the case of clumped touching nu- clei. Early results show that we can reach a 91% detec- tion rate compared to manual ground truth of cell nuclei centers across a range of prostate cancer grades.