Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches

TL;DR

This paper presents a deep learning-based system for automatic colon polyp detection in colonoscopy images and videos, utilizing region-based CNNs, data augmentation, and post-learning methods to improve accuracy and reduce false positives.

Contribution

It introduces a novel combination of region-based deep CNNs with post-learning schemes for enhanced polyp detection in colonoscopy data.

Findings

Improved detection accuracy over existing methods

Effective false positive reduction techniques

Enhanced video detection performance

Abstract

Automatic detection of colonic polyps is still an unsolved problem due to the large variation of polyps in terms of shape, texture, size, and color, and the existence of various polyp-like mimics during colonoscopy. In this study, we apply a recent region based convolutional neural network (CNN) approach for the automatic detection of polyps in images and videos obtained from colonoscopy examinations. We use a deep-CNN model (Inception Resnet) as a transfer learning scheme in the detection system. To overcome the polyp detection obstacles and the small number of polyp images, we examine image augmentation strategies for training deep networks. We further propose two efficient post-learning methods such as, automatic false positive learning and off-line learning, both of which can be incorporated with the region based detection system for reliable polyp detection. Using the large size of colonoscopy databases, experimental results demonstrate that the suggested detection systems show better performance compared to other systems in the literature. Furthermore, we show improved detection performance using the proposed post-learning schemes for colonoscopy videos.