Paper Title
Detection and Instance Segmentation of Colon Polyps in Colonoscopy Images

Abstract
Colorectal cancer is one of the main causes of cancer death worldwide. Polyp growth on the inner lining of the colon or rectum can change into cancer, over time. Early detection and diagnosis of polyp are key to ensure the survival of a patient. Detection and segmentation of polyps in colonoscopy is a challenging task due to the variations in size, shape, the texture of polyps, and variations between polyps and hard mimics. Colonoscopy is the most efficient method for polyp screening and detection, however, it is operator-dependent, time-consuming, and error prone. Sometimes polyps are missed or hard to detect in colonoscopy. In recent years many efficient deep learning techniques are introduced for polyp segmentation. In this paper, we employed an object detection neural network "Mask R-CNN with Inception Resnet v2" as the bacbone for the detection and instance segmentation of polyps using Kvasir-SEG dataset. Keywords - Colorectal cancer, Colonoscopy, Polyp, segmentation