Can Adversarial Networks Make Uninformative Colonoscopy Video Frames Clinically Informative?

TL;DR

This paper introduces an adversarial network framework to transform uninformative colonoscopy video frames into clinically relevant ones, improving polyp detection performance and addressing artifacts like motion blur and ghosting.

Contribution

The study proposes a novel adversarial network approach to enhance uninformative colonoscopy frames, improving diagnostic utility and detection accuracy over existing methods.

Findings

Improved polyp detection performance with the proposed method

Qualitative results show more clinically relevant frames

Analysis of failure cases guides future improvements

Abstract

Various artifacts, such as ghost colors, interlacing, and motion blur, hinder diagnosing colorectal cancer (CRC) from videos acquired during colonoscopy. The frames containing these artifacts are called uninformative frames and are present in large proportions in colonoscopy videos. To alleviate the impact of artifacts, we propose an adversarial network based framework to convert uninformative frames to clinically relevant frames. We examine the effectiveness of the proposed approach by evaluating the translated frames for polyp detection using YOLOv5. Preliminary results present improved detection performance along with elegant qualitative outcomes. We also examine the failure cases to determine the directions for future work.