Automatic polyp detection of colon using high resolution CT scans

Abstract

Automatic detection of polyps can be a valuable tool for diagnoses of early colorectal cancer as early detection and hence removal of polyps can save life. Polyp detection is a challenging task as polyps come in different sizes and shapes. The detection generally consists of three stages: 1) colon segmentation, 2) identification of suspected polyps and 3) polyp classification. The latter involves classifying polyps from among many suspected regions. This paper concentrates on the first two stages of the detection. For the colon segmentation, the fuzzy connectivity region growing technique is used while for the identification of suspected polyps concave region searching is applied. The method is fast, robust and validated with a number of high-resolution colon datasets.