Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network

TL;DR

This paper presents a convolutional neural network-based method for polyp segmentation in colonoscopy images, improving accuracy through novel training and post-processing strategies, aiding early colorectal cancer diagnosis.

Contribution

Introduces a new CNN-based polyp segmentation approach with innovative patch selection and post-processing techniques for better accuracy.

Findings

Achieves higher segmentation accuracy than previous methods

Effective patch selection improves training efficiency

Post-processing enhances the quality of probability maps

Abstract

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