Faculty, Staff and Student Publications
Language
English
Publication Date
1-1-2026
Journal
Frontiers in Endocrinology
DOI
10.3389/fendo.2026.1869015
PMID
42523658
PMCID
PMC13407100
PubMedCentral® Posted Date
7-14-2026
PubMedCentral® Full Text Version
Post-print
Abstract
Introduction: Accurate detection of gastrointestinal diseases from endoscopic images remains challenging due to substantial inter-class similarity, intra-class variability, and heterogeneous lesion presentation. While convolutional neural networks (CNNs) effectively capture fine mucosal textures, their limited receptive field restricts global contextual reasoning. Conversely, transformer architectures model long-range dependencies but may underrepresent localized structural detail.
Methods: This study proposes a dual-branch hybrid transformer framework that integrates global token-level reasoning from ViT-L/32 with hierarchical spatial modeling from MaxViT-L. An adaptive gated fusion mechanism is introduced to dynamically regulate the relative contribution of local and global representations on a per-sample basis, enabling content-aware cross-scale integration. The model was evaluated on a multi-class gastrointestinal endoscopic dataset using comprehensive quantitative metrics, class-wise analysis, ablation studies, confidence interval estimation, and statistical validation. Post-hoc explainability was further investigated using multiple complementary XAI techniques.
Results: The proposed framework demonstrated consistently high accuracy, sensitivity, specificity, and area under the ROC curve across eight gastrointestinal disease categories, outperforming several state-of-the-art transformer and hybrid architectures. The XAI analyses further confirmed lesion-focused activation consistency and stable decision-making.
Discussion: The findings indicate that adaptive local-global feature integration through gated fusion enhances both diagnostic performance and interpretability, supporting the potential of hybrid transformer architectures for reliable computer-aided gastrointestinal disease classification.
Keywords
Gastrointestinal Diseases, Humans, Convolutional Neural Networks, Endoscopy, Gastrointestinal, Image Interpretation, Computer-Assisted, Neural Networks, Computer, adaptive gated fusion, endoscopic image classification, explainable AI, gastrointestinal disease detection, hybrid transformer architecture, vision transformer
Published Open-Access
yes
Recommended Citation
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, and Zhongming Zhao, "A Hybrid ViT-L/32-MaxViT-L Architecture With Adaptive Gated Fusion for Multiclass Gastrointestinal Disease Detection and Multi-method post-hoc Explainability" (2026). Faculty, Staff and Student Publications. 1029.
https://digitalcommons.library.tmc.edu/uthshis_docs/1029