Combination of Handcrafted Features and Deep Learning-Based Features for Improved Colon Disease Detection (Preprint)

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. CLINICALTRIAL