ColonNet: A Hybrid Of DenseNet121 And U-NET Model For Detection And Segmentation Of GI Bleeding

TL;DR

This paper introduces ColonNet, a hybrid DenseNet and U-Net deep learning model that detects and segments gastrointestinal bleeding in wireless capsule endoscopy videos, achieving high accuracy and aiding medical diagnosis.

Contribution

The study develops a novel hybrid model combining DenseNet and U-Net for improved GI bleeding detection and segmentation in complex real-world datasets.

Findings

Achieved 80% overall accuracy in bleeding detection.

Outperformed 74 other teams in the Auto-WCBleedGen Challenge.

Demonstrated effective segmentation of bleeding areas.

Abstract

This study presents an integrated deep learning model for automatic detection and classification of Gastrointestinal bleeding in the frames extracted from Wireless Capsule Endoscopy (WCE) videos. The dataset has been released as part of Auto-WCBleedGen Challenge Version V2 hosted by the MISAHUB team. Our model attained the highest performance among 75 teams that took part in this competition. It aims to efficiently utilizes CNN based model i.e. DenseNet and UNet to detect and segment bleeding and non-bleeding areas in the real-world complex dataset. The model achieves an impressive overall accuracy of 80% which would surely help a skilled doctor to carry out further diagnostics.