Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video
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 bleedi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/8327/ http://eprints.uthm.edu.my/8327/1/J15680_b5b5a9ffedc5b53bec21607394f04dc4.pdf |
| _version_ | 1848889365152923648 |
|---|---|
| author | Vajravelua, Ashok Tamil Selvan, K.S. Abdul Jamil, Muhammad Mahadi Jude, Anitha Torre Diez, Isabel de la |
| author_facet | Vajravelua, Ashok Tamil Selvan, K.S. Abdul Jamil, Muhammad Mahadi Jude, Anitha Torre Diez, Isabel de la |
| author_sort | Vajravelua, Ashok |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-15T20:25:01Z |
| format | Article |
| id | uthm-8327 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:25:01Z |
| publishDate | 2023 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-83272023-02-15T07:08:08Z http://eprints.uthm.edu.my/8327/ Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video Vajravelua, Ashok Tamil Selvan, K.S. Abdul Jamil, Muhammad Mahadi Jude, Anitha Torre Diez, Isabel de la TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television 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. 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/8327/1/J15680_b5b5a9ffedc5b53bec21607394f04dc4.pdf Vajravelua, Ashok and Tamil Selvan, K.S. and Abdul Jamil, Muhammad Mahadi and Jude, Anitha and Torre Diez, Isabel de la (2023) Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video. Journal of Intelligent & Fuzzy Systems, 44. pp. 353-364. https://doi.org/10.3233/JIFS-213099 |
| spellingShingle | TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television Vajravelua, Ashok Tamil Selvan, K.S. Abdul Jamil, Muhammad Mahadi Jude, Anitha Torre Diez, Isabel de la Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title_full | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title_fullStr | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title_full_unstemmed | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title_short | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| title_sort | machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video |
| topic | TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television |
| url | http://eprints.uthm.edu.my/8327/ http://eprints.uthm.edu.my/8327/ http://eprints.uthm.edu.my/8327/1/J15680_b5b5a9ffedc5b53bec21607394f04dc4.pdf |