Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review

TL;DR

This review paper discusses the challenges and recent approaches in automatic polyp detection and segmentation in video capsule endoscopy, emphasizing the unique difficulties posed by VCE imagery compared to traditional endoscopy.

Contribution

It provides a systematic analysis of existing polyp detection methods for VCE and highlights the challenges specific to this imaging modality.

Findings

Various detection algorithms have been proposed with differing success levels.

Detecting polyps in VCE is more challenging than in traditional endoscopy.

Standard image processing methods face significant hurdles in VCE analysis.

Abstract

Video capsule endoscopy (VCE) is used widely nowadays for visualizing the gastrointestinal (GI) tract. Capsule endoscopy exams are prescribed usually as an additional monitoring mechanism and can help in identifying polyps, bleeding, etc. To analyze the large scale video data produced by VCE exams automatic image processing, computer vision, and learning algorithms are required. Recently, automatic polyp detection algorithms have been proposed with various degrees of success. Though polyp detection in colonoscopy and other traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics detecting polyps automatically in VCE is a hard problem. We review different polyp detection approaches for VCE imagery and provide systematic analysis with challenges faced by standard image processing and computer vision methods.