A Classification-Enhanced Vote Accumulation Scheme for Detecting Colonic Polyps

Colorectal cancer most often begins as abnormal growth of the colon wall, commonly referred to as polyps. It has been shown that the timely removal of polyps with optical colonoscopy (OC) significantly reduces the incidence and mortality of colorectal cancer. However, a significant number of polyps are missed during OC in clinical practice—the pooled miss-rate for all polyps is 22% (95% CI, 19%–26%). Computer-aided detection may offer promises of reducing polyp miss-rate. This paper proposes a new automatic polyp detection method. Given a colonoscopy image, the main idea is to identify the edge pixels that lie on the boundary of polyps and then determine the location of a polyp from the identified edges. To do so, we first use the Canny edge detector to form a crude set of edge pixels, and then apply a set of boundary classifiers to remove a large portion of irrelevant edges. The polyp locations are then determined by a novel vote accumulation scheme that operates on the positively classified edge pixels. We evaluate our method on 300 images from a publicly available database and obtain results superior to the state-of-the-art performance.