Automated bleeding detection in wireless capsule endoscopy images based on sparse coding
- PDF / 3,840,007 Bytes
- 14 Pages / 439.642 x 666.49 pts Page_size
- 60 Downloads / 270 Views
Automated bleeding detection in wireless capsule endoscopy images based on sparse coding Abhinav Patel1 · Kumi Rani1 · Sunil Kumar1 Pedro N. Figueiredo3,4
· Isabel N. Figueiredo2 ·
Received: 23 January 2020 / Revised: 22 July 2020 / Accepted: 12 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Wireless Capsule Endoscopy (WCE) is a revolutionary technique for screening of gastrointestinal (GI) tract. However, WCE needs automated methods to reduce the time required for viewing its large image data and also to improve the accuracy of inspection. In this work, we propose novel sparse coded features to detect bleeding in WCE images. We acquire Scale-Invariant Feature Transform (SIFT) based key points as regions of interest of an image. Further, we compute SIFT and uniform Local Binary Pattern (LBP) features around the key points from an image. After that sparse coded features are obtained and support vector machine (SVM) is used for image classification. We provide comprehensive experimental results and also comparison with some recent bleeding detection methods and with traditional ways of computing sparse coded features. The best results are obtained with a dictionary size of 300 atoms. The classification accuracy we achieve with the proposed approach is 98.18%. The results presented in the paper indicate that the proposed method is reliable for bleeding detection in WCE images. Sunil Kumar
[email protected]; [email protected] Abhinav Patel [email protected] Kumi Rani [email protected] Isabel N. Figueiredo [email protected] Pedro N. Figueiredo [email protected] 1
Department of Mathematical Sciences, Indian Institute of Technology (BHU) Varanasi, Varanasi, 221005, Uttar Pradesh, India
2
Department of Mathematics (CMUC) - Faculty of Sciences and Technology, University of Coimbra, Coimbra, Portugal
3
Faculty of Medicine, University of Coimbra, Coimbra, Portugal
4
Department of Gastroenterology, CHUC (Centro Hospitalar e Universit´ario de Coimbra), Coimbra, Portugal
Multimedia Tools and Applications
Keywords Wireless Capsule Endoscopy · Bleeding detection · Sparse coding · Dictionary learning
1 Introduction In recent times there has been a great technological progress in the field of medical imaging. Wireless Capsule Endoscopy (WCE) [11] is one of the major evolution in this field. Although, conventional gastroscopy and colonoscopy are still in use for examining the gastrointestinal (GI) tract, WCE is widely made in use for inspection of small intestine, reaching where it is very hard to reach with the traditional endoscopy techniques such as colonoscopy, push enteroscopy and intraoperative enteroscopy. In WCE, the doctors and clinicians do not have to follow the examination process continuously. Instead, they have to deal with the data recorded by the capsule after it has passed through the entire gastrointestinal tract. Doctors have to examine around 8 hours video or around 55000 images and select the ones in which they find any abnormal
Data Loading...
