Computer-Aided Bleeding Detection in WCE Video

• Published in: IEEE journal of biomedical and health informatics Vol. 18; no. 2; pp. 636 - 642
• Main Authors: Fu, Yanan, Zhang, Wei, Mandal, Mrinal, Meng, Max Q.-H.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bleeding detection; Capsule Endoscopy - methods; Endoscopes; Gastrointestinal Hemorrhage - diagnosis; Gastrointestinal Hemorrhage - pathology; Hemorrhaging; Humans; Image color analysis; Image edge detection; Image Interpretation, Computer-Assisted - methods; Image segmentation; Intestines; Intestines - pathology; Sensitivity and Specificity; Small intestine; superpixel; Support Vector Machine; Support vector machines; wireless capsule endoscopy (WCE)
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2013.2257819

Wireless capsule endoscopy (WCE) can directly take digital images in the gastrointestinal tract of a patient. It has opened a new chapter in small intestine examination. However, a major problem associated with this technology is that too many images need to be manually examined by clinicians. Currently, there is no standard for capsule endoscopy image interpretation and classification. Most state-of-the-art CAD methods often suffer from poor performance, high computational cost, or multiple empirical thresholds. In this paper, a new method for rapid bleeding detection in the WCE video is proposed. We group pixels through superpixel segmentation to reduce the computational complexity while maintaining high diagnostic accuracy. Feature of each superpixel is extracted using the red ratio in RGB space and fed into support vector machine for classification. Also, the influence of edge pixels has been removed in this paper. Comparative experiments show that our algorithm is superior to the existing methods in terms of sensitivity, specificity, and accuracy.