Performance Comparison of Deep Learning Architectures for Artifact Removal in Gastrointestinal Endoscopic Imaging

TL;DR

This paper compares seven different CNN architectures to evaluate their effectiveness in removing surgical instrument artifacts from gastrointestinal endoscopic images, aiming to improve image analysis accuracy in medical diagnostics.

Contribution

It provides a systematic comparison of CNN architectures specifically for artifact removal in endoscopic images, highlighting the most effective models for this task.

Findings

Certain CNN architectures outperform others in artifact removal accuracy.

The study identifies the best architecture for surgical instrument artifact removal.

Results suggest specific models are more suitable for clinical endoscopic image enhancement.

Abstract

Endoscopic images typically contain several artifacts. The artifacts significantly impact image analysis result in computer-aided diagnosis. Convolutional neural networks (CNNs), a type of deep learning, can removes such artifacts. Various architectures have been proposed for the CNNs, and the accuracy of artifact removal varies depending on the choice of architecture. Therefore, it is necessary to determine the artifact removal accuracy, depending on the selected architecture. In this study, we focus on endoscopic surgical instruments as artifacts, and determine and discuss the artifact removal accuracy using seven different CNN architectures.