Open Access

ARTICLE

DeepNeck: Bottleneck Assisted Customized Deep Convolutional Neural Networks for Diagnosing Gastrointestinal Tract Disease

Sidra Naseem¹, Rashid Jahangir^1,*, Nazik Alturki², Faheem Shehzad³, Muhammad Sami Ullah⁴

1 Department of Computer Science, COMSATS University Islamabad, Vehari Campus, Vehari, 61100, Pakistan
2 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
3 Department of Electrical Engineering and Information Technology (DIETI), University of Naples “Federico II”, Naples, 80138, Italy
4 Department of Computer Science, University of Gujrat, Gujrat, 50700, Pakistan

* Corresponding Author: Rashid Jahangir. Email:

(This article belongs to the Special Issue: Artificial Intelligence Models in Healthcare: Challenges, Methods, and Applications)

Computer Modeling in Engineering & Sciences 2025, 145(2), 2481-2501. https://doi.org/10.32604/cmes.2025.072575

Received 29 August 2025; Accepted 15 October 2025; Issue published 26 November 2025

Abstract

Diagnosing gastrointestinal tract diseases is a critical task requiring accurate and efficient methodologies. While deep learning models have significantly advanced medical image analysis, challenges such as imbalanced datasets and redundant features persist. This study proposes a novel framework that customizes two deep learning models, NasNetMobile and ResNet50, by incorporating bottleneck architectures, named as NasNeck and ResNeck, to enhance feature extraction. The feature vectors are fused into a combined vector, which is further optimized using an improved Whale Optimization Algorithm to minimize redundancy and improve discriminative power. The optimized feature vector is then classified using artificial neural network classifiers, effectively addressing the limitations of traditional methods. Data augmentation techniques are employed to tackle class imbalance, improving model learning and generalization. The proposed framework was evaluated on two publicly available datasets: Hyper-Kvasir and Kvasir v2. The Hyper-Kvasir dataset, comprising 23 gastrointestinal disease classes, yielded an impressive 96.0% accuracy. On the Kvasir v2 dataset, which contains 8 distinct classes, the framework achieved a remarkable 98.9% accuracy, further demonstrating its robustness and superior classification performance across different gastrointestinal datasets. The results demonstrate the effectiveness of customizing deep models with bottleneck architectures, feature fusion, and optimization techniques in enhancing classification accuracy while reducing computational complexity.

---

Keywords

---