A. Hafiane, F. Bunyak, and K. Palaniappan

IEEE Int. Conf. Pattern Recognition, pgs. Online, 2008

histopathology, active contours, classification, segmentation, features, biomedical

PlainText, Bibtex, PDF, URL, DOI, Google Scholar

Abstract

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.