Saved in:
Bibliographic Details
Main Authors: Houmaidi, Walid, Hadadi, Mohamed, Sabiri, Youssef, Chtouki, Yousra
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.21959
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909928355004416
author Houmaidi, Walid
Hadadi, Mohamed
Sabiri, Youssef
Chtouki, Yousra
author_facet Houmaidi, Walid
Hadadi, Mohamed
Sabiri, Youssef
Chtouki, Yousra
contents This paper presents a comprehensive comparative model analysis on a novel gastrointestinal medical imaging dataset, comprised of 4,000 endoscopic images spanning four critical disease classes: Diverticulosis, Neoplasm, Peritonitis, and Ureters. Leveraging state-of-the-art deep learning techniques, the study confronts common endoscopic challenges such as variable lighting, fluctuating camera angles, and frequent imaging artifacts. The best performing models, VGG16 and MobileNetV2, each achieved a test accuracy of 96.5%, while Xception reached 94.24%, establishing robust benchmarks and baselines for automated disease classification. In addition to strong classification performance, the approach includes explainable AI via Grad-CAM visualization, enabling identification of image regions most influential to model predictions and enhancing clinical interpretability. Experimental results demonstrate the potential for robust, accurate, and interpretable medical image analysis even in complex real-world conditions. This work contributes original benchmarks, comparative insights, and visual explanations, advancing the landscape of gastrointestinal computer-aided diagnosis and underscoring the importance of diverse, clinically relevant datasets and model explainability in medical AI research.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepGI: Explainable Deep Learning for Gastrointestinal Image Classification
Houmaidi, Walid
Hadadi, Mohamed
Sabiri, Youssef
Chtouki, Yousra
Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Machine Learning
I.2.10; I.4.6; J.3
This paper presents a comprehensive comparative model analysis on a novel gastrointestinal medical imaging dataset, comprised of 4,000 endoscopic images spanning four critical disease classes: Diverticulosis, Neoplasm, Peritonitis, and Ureters. Leveraging state-of-the-art deep learning techniques, the study confronts common endoscopic challenges such as variable lighting, fluctuating camera angles, and frequent imaging artifacts. The best performing models, VGG16 and MobileNetV2, each achieved a test accuracy of 96.5%, while Xception reached 94.24%, establishing robust benchmarks and baselines for automated disease classification. In addition to strong classification performance, the approach includes explainable AI via Grad-CAM visualization, enabling identification of image regions most influential to model predictions and enhancing clinical interpretability. Experimental results demonstrate the potential for robust, accurate, and interpretable medical image analysis even in complex real-world conditions. This work contributes original benchmarks, comparative insights, and visual explanations, advancing the landscape of gastrointestinal computer-aided diagnosis and underscoring the importance of diverse, clinically relevant datasets and model explainability in medical AI research.
title DeepGI: Explainable Deep Learning for Gastrointestinal Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Machine Learning
I.2.10; I.4.6; J.3
url https://arxiv.org/abs/2511.21959