Effect of Various Image Information in Polyp Classification by Deeping Learning with Small Dataset

Clinical colonoscopy is the gold standard for polyp detection and resection in clinic. A main challenge in the polyp identification by deep learning is the limited patients number. In this paper, we discussed the usage of various image layers which provide and emphasize different image information in the polyp recognition and polyp classification. The results showed that comparing with the intensity image in RGB color space, the gradient images and images in chromaticity color space may provide more critical character to the deep learning model, and achieve a better performance with small training dataset.