ORCID

http://orcid.org/0000-0002-3565-7390

Document Type

Article

CIT Disciplines

1.2 COMPUTER AND INFORMATION SCIENCE; Bioinformatics; 1.6 BIOLOGICAL SCIENCES

Disciplines

Computer Sciences | Diagnosis | Diseases | Gastroenterology

Publication Details

Biomedical Signal Processing and Control, Volume 56, February 2020, 101668.

Abstract

Computer-aided diagnosis of gastric diseases from endoscopy frames is an important task. It facilitates both the patient and gastroenterologist in terms of time, money and most important health. Colors are the basic visual features of endoscopic images and also provide clues about abnormal regions in endoscopy frames. A variety of color spaces available for representation of color frames. However, we are not certain about which color space is more suitable for representing color features of gastric images. This paper presents a comparison of color features in different color spaces for detection of abnormal areas in chromoendoscopy (CH) frames. In addition, the CH images are segmented by using an existing color-difference based segmentation method Delta E (ΔE). A framework for automatic segmentation is presented for endoscopy images by selecting a template image in ΔE by using trained models. For classification, colors features are also merged with texture descriptors. The support vector machine (SVM) classifier is trained on color features and also the hybrid color combined texture characteristics. Then the trained classifier is used to group CH frames into abnormal and normal classes. ΔE with manual template selection has achieved 57.44% accuracy and 56.88% accuracy with the automated process. Moreover, the suggested method achieves 86.6% accuracy and 0.91 area under the curve for the classification of gastric lesions.

Available for download on Tuesday, February 01, 2022

Share

COinS