Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video

• Main Authors: Ashok Vajravelu, Ashok Vajravelu, K.S. Tamil Selvan, K.S. Tamil Selvan, Abdul Jamil, Muhammad Mahadi, Anitha Jude, Anitha Jude, Isabel de la Torre Diez, Isabel de la Torre Diez
• Format: Article
• Language: English
• Published: 2023
• Subjects: T Technology (General)
• Online Access: http://eprints.uthm.edu.my/9292/1/J15680_b5b5a9ffedc5b53bec21607394f04dc4.pdf; http://eprints.uthm.edu.my/9292/; https://doi.org/10.3233/JIFS-213099

Wireless Capsule Endoscopy (WCE) allows direct visual inspecting of the full digestive system of the patient without invasion and pain, at the price of a long examination by physicians of a large number of photographs. This research presents a new approach to color extraction to differentiate bleeding frames from normal ones and locate more bleeding areas. We have a dual-system suggestion. We use entire color information on the WCE pictures and the pixel-represented clustering approach to get the clustered centers that characterize WCE pictures as words. Then we evaluate the status of a WCE framework using the nearby SVM and K methods (KNN). The classification performance is 95.75% accurate for the AUC 0.9771% and validates the exciting performance for bleeding classification provided by the suggested approach. Second, we present a two-step approach for extracting saliency maps to emphasize bleeding locations with a distinct color channel mixer to build a first-stage salience map. The second stage salience map was taken with optical contrast.We locate bleeding spots following a suitable fusion approach and threshold. Quantitative and qualitative studies demonstrate that our approaches can correctly distinguish bleeding sites from neighborhoods.