Deep CNN and Geometric Features-Based Gastrointestinal Tract Diseases Detection and Classification from Wireless Capsule Endoscopy Images
Published in Journal of Experimental & Theoretical Artificial Intelligence (Taylor & Francis), 2019
Authors:
Muhammad Sharif, Muhammad Attique Khan, Muhammad Rashid, Mussarat Yasmin, Farhat Afza, Urcun John Tanik
This work presents a framework for gastrointestinal tract disease detection and classification using wireless capsule endoscopy (WCE) images. The proposed approach combines deep convolutional neural network (CNN) features with geometric features to improve classification performance and robustness.
Contributions 📃
- A hybrid framework combining deep CNN features and geometric features.
- Improved detection and classification of gastrointestinal diseases from WCE images.
- Feature fusion strategy for enhanced discriminative representation.
- Evaluation on medical datasets demonstrating improved performance.
📖 Citation (BibTeX)
@article{sharif2021deep,
title = {Deep CNN and Geometric Features-Based Gastrointestinal Tract Diseases Detection and Classification from Wireless Capsule Endoscopy Images},
author = {Sharif, Muhammad and Khan, Muhammad Attique and Rashid, Muhammad and Yasmin, Mussarat and Afza, Farhat and Tanik, Urcun John},
journal = {Journal of Experimental \& Theoretical Artificial Intelligence},
volume = {33},
number = {4},
pages = {577--599},
year = {2021},
publisher = {Taylor \& Francis},
doi = {10.1080/0952813X.2019.1572657}
}