| Title |
Computer-aided system for bleeding detection in WCE images based on CNN-GRU network |
| ID_Doc |
61908 |
| Authors |
Lafraxo, S; El Ansari, M; Koutti, L |
| Title |
Computer-aided system for bleeding detection in WCE images based on CNN-GRU network |
| Year |
2024 |
| Published |
Multimedia Tools And Applications, 83.0, 7 |
| DOI |
10.1007/s11042-023-16305-w |
| Abstract |
Wireless capsule endoscopy (WCE) is a non-invasive video technique used to investigate gastrointestinal diseases such as hemorrhage, ulcer, and polyp. Automatic detection systems that primarily use features derived from WCE images are being developed in order to bypass a difficult and time-consuming manual evaluation procedure. Bleeding is one the most prevalent anomalies in WCE images, This anomaly can be identified by its color features. In this paper, a computer-aided approach for detecting bleeding frames is proposed. The suggested system consists of three major phases: preprocessing, feature extraction using optimized convolutional neural network (CNN), and classification based on gated recurrent unit (GRU). We investigate our proposed CNN-GRU based methodology using a publicly available dataset called MICCAI 2017, and the results of the experiments demonstrate that our strategy is both efficient and robust, achieving high accuracy of 99.39% with considerable performance gains over the state-of-the-art. |
| Author Keywords |
Wireless capsule endoscopy; Bleeding; Deep learning; Convolutional neural network; Reccurent neural network; Classification; Gated recurrent unit |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:001037378900010 |
| WoS Category |
Computer Science, Information Systems; Computer Science, Software Engineering; Computer Science, Theory & Methods; Engineering, Electrical & Electronic |
| Research Area |
Computer Science; Engineering |
| PDF |
|