# Integrating Deep Feature Extraction and Hybrid ResNet-DenseNet Model for Multi-Class Abnormality Detection in Endoscopic Images

arXiv: https://arxiv.org/abs/2410.18457 · HTML: https://mlsanity.com/paper/2410.18457/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 2 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 1 of 1)

- [Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy](https://mlsanity.com/paper/2408.04940/) (2024)

## Built on by (most cited first, 1 of 1)

- [Optimizing Gastrointestinal Diagnostics: A CNN-Based Model for VCE Image Classification](https://mlsanity.com/paper/2411.01652/) (2024)

## Abstract (arXiv)

This paper presents a deep learning framework for the multi-class classification of gastrointestinal abnormalities in Video Capsule Endoscopy (VCE) frames. The aim is to automate the identification of ten GI abnormality classes, including angioectasia, bleeding, and ulcers, thereby reducing the diagnostic burden on gastroenterologists. Utilizing an ensemble of DenseNet and ResNet architectures, the proposed model achieves an overall accuracy of 94% across a well-structured dataset. Precision scores range from 0.56 for erythema to 1.00 for worms, with recall rates peaking at 98% for normal findings. This study emphasizes the importance of robust data preprocessing techniques, including normalization and augmentation, in enhancing model performance. The contributions of this work lie in developing an effective AI-driven tool that streamlines the diagnostic process in gastroenterology, ultimately improving patient care and clinical outcomes.