Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow

Abstract—Today’s computer aided detection systems for com-puted tomography colonography (CTC) enable automated detec-tion and segmentation of colorectal polyps. We present a paradigm shift by proposing a method that measures the amount of protrud-edness of a candidate object in a scale adaptive fashion. One of the main results is that the performance of the candidate detection de-pends only on one parameter, the amount of protrusion. Addition-ally the method yields correct polyp segmentation without the need of an additional segmentation step. The supervised pattern recog-nition involves a clear distinction between size related features and features related to shape or intensity. A Mahalanobis transforma-tion of the latter facilitates ranking of the objects using a logistic classifier. We evaluate two implementations of the method on 84 patients with a total of 57 polyps larger than or equal to 6 mm. We obtained a performance of 95 % sensitivity at four false positives per scan for polyps larger than or equal to 6 mm. Index Terms—Biomedical image processing, image analysis, par-tial differential equation (PDE), polyp detection, surface evolution. I