ORIGINAL RESEARCH article
Front. Med. Eng.
Sec. Computational Medicine
WAVELET-ENHANCED DEEP FEATURE FUSION AND GREY SAIL FISH OPTIMIZATION FOR GASTROINTESTINAL DISEASE CLASSIFICATION
Provisionally accepted
Sharmila V
Geetha S*- VIT University Chennai, Chennai, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract: Gastrointestinal (GI) diseases, including cancers and bleeding disorders, pose significant health risks worldwide, necessitating early and accurate diagnosis for effective treatment. Traditional diagnostic methods such as endoscopy and colonoscopy are time-consuming, require expert interpretation, and are prone to human errors. To address these challenges, this research proposes a novel deep learning-based framework for automated GI disease classification using Wavelet Enhanced Res-Google Feature Fusion Net (WERG-FFN) and Optimized Hybrid Serial-Paralleled Fusion (OHSP-Fusion). The proposed approach integrates Discrete Wavelet Transform (DWT) for enhanced feature extraction, combines ResNet50 and GoogleNet for deep feature representation, and employs Optimized Grey Sail Fish Optimization (OGSF) Algorithm for optimal feature selection. Finally, for the disease classification, a Linear Kernel Support Vector Machine (LK-SVM) is used which ensures robust and efficient disease categorization. Experimentation has been carried out by using the Kvasir-v1 containing images segregated into lower GI diseases such as polyps, dyed-lifted polyps, normal cecum, normal pylorus, and ulcerative colitis. The suggested technique attains accuracy rate of 99.79%.
Keywords: Adaptive Probability Filter (APF), Feature fusion, Gastro-Intestinal (GI) Diseases, Multi-Head Attention Model, wireless capsule endoscopy (WCE)
Received: 01 Dec 2025; Accepted: 09 Feb 2026.
Copyright: © 2026 V and S. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Geetha S
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.