Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network

Colorectal cancer is a one of the highest causes of cancer-related death, in men. Polyps are one of the main causes of colorectal cancer and diagnosis of polyps by colonoscopy could result in successful treatment. of polyps in colonoscopy videos is a challenging task due to in the size and shape of polyps. In this paper we proposed a polyp method based on convolutional neural network. Performance of the is enhanced by two strategies. First, we perform a novel image patch method in the training phase of the network. Second, in the test, we perform an effective post processing on the probability map that is by the network. Evaluation of the proposed method using the-ColonDB database shows that our proposed method achieves more accurate in comparison with previous colonoscopy video-segmentation methods.