Previously submitted to: JMIR Biomedical Engineering (no longer under consideration since May 04, 2026)
Date Submitted: Sep 23, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Combination of Handcrafted Features and Deep Learning-Based Features for Improved Colon Disease Detection
ABSTRACT
Background:
In order to lower the risk of colorectal cancer, colon disorders like polyps, ulcers, and IBD must be detected early. However, human processing of WCE images is laborious and prone to mistakes.
Objective:
To create a deep learning-based and handcrafted feature-based automated diagnostic framework for better colon illness identification.
Methods:
Using CNNs to extract texture, color, and form descriptors as handcrafted features and hierarchical representations, followed by feature fusion and classification, a hybrid technique was created.
Results:
The suggested methodology outperformed handcrafted-only and deep-learning-only methods with 96.3% accuracy, 95.7% sensitivity, and 97.1% specificity on a benchmark WCE dataset.
Conclusions:
Combining deep learning and handmade features improves classification performance, providing a practical and efficient approach for early identification of colon illness.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.