Influence of color correction on pathology detection in Capsule Endoscopy

TL;DR

This study investigates how color correction affects deep learning models' ability to detect pathologies in Wireless Capsule Endoscopy images, revealing mixed impacts on detection accuracy and false positives.

Contribution

It provides a comparative analysis of the effects of color correction on two prominent object detection models in WCE pathology detection.

Findings

Color correction results in larger bounding boxes and intersection areas.

Color correction increases false positives for some pathologies.

No consistent improvement in detection performance metrics was observed.

Abstract

Pathology detection in Wireless Capsule Endoscopy (WCE) using deep learning has been explored in the recent past. However, deep learning models can be influenced by the color quality of the dataset used to train them, impacting detection, segmentation and classification tasks. In this work, we evaluate the impact of color correction on pathology detection using two prominent object detection models: Retinanet and YOLOv5. We first generate two color corrected versions of a popular WCE dataset (i.e., SEE-AI dataset) using two different color correction functions. We then evaluate the performance of the Retinanet and YOLOv5 on the original and color corrected versions of the dataset. The results reveal that color correction makes the models generate larger bounding boxes and larger intersection areas with the ground truth annotations. Furthermore, color correction leads to an increased number of false positives for certain pathologies. However, these effects do not translate into a consistent improvement in performance metrics such as F1-scores, IoU, and AP50. The code is available at https://github.com/agossouema2011/WCE2024. Keywords: Wireless Capsule Endoscopy, Color correction, Retinanet, YOLOv5, Detection