Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186996,
        author = {Hemanth T S and Hemalatha B M and Chinmayi M U and Vijayalaxmi and Hemanth P and Manoj H P},
        title = {A Comprehensive Review on Gastrointestinal Disease Detection and Classification Using a Tailored Convolutional Neural Network Layer},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4479-4492},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186996},
        abstract = {Gastrointestinal (GI) diseases represent a significant global health burden, with endoscopy being the primary diagnostic tool, though manual image analysis is time-consuming and prone to human error, potentially delaying treatment. Deep learning, particularly Convolutional Neural Networks (CNNs), offers an automated and accurate solution for disease classification, with this review comprehensively analyzing techniques such as foundational CNN architectures (e.g., ResNet), hybrid and ensemble models, and transformer-based systems, alongside feature extraction strategies, data preprocessing methods, and public datasets like KVASIR Research has proven that, for many applications, hybrid and ensemble models show superior accuracy, often more than 98%, by mixing diverse architectures, while different types of augmentations and strategies to counter class imbalance, BL-SMOTE for example, show a considerable improvement in robustness. Despite this, there were still some problems such as costs of computing, large annotated datasets and lack of interpretability. Hence, future work must focus on light-weight models for real-time use in clinics and explainable-AI (XAI) for greater trust and adoption in practice.},
        keywords = {Endoscopy, Deep Learning, Convolutional Neural Networks (CNN), ResNet101V2, Alimentary Tract},
        month = {November},
        }