Dimitris K Iakovidis1, Anastasios Koulaouzidis2. 1. Department of Computer Engineering, Technological Educational Institute of Central Greece, Lamia, Greece. 2. Endoscopy Unit, The Royal Infirmary of Edinburgh, Edinburgh, United Kingdom.
Abstract
BACKGROUND: The advent of wireless capsule endoscopy (WCE) has revolutionized the diagnostic approach to small-bowel disease. However, the task of reviewing WCE video sequences is laborious and time-consuming; software tools offering automated video analysis would enable a timelier and potentially a more accurate diagnosis. OBJECTIVE: To assess the validity of innovative, automatic lesion-detection software in WCE. DESIGN/INTERVENTION: A color feature-based pattern recognition methodology was devised and applied to the aforementioned image group. SETTING: This study was performed at the Royal Infirmary of Edinburgh, United Kingdom, and the Technological Educational Institute of Central Greece, Lamia, Greece. MATERIALS: A total of 137 deidentified WCE single images, 77 showing pathology and 60 normal images. RESULTS: The proposed methodology, unlike state-of-the-art approaches, is capable of detecting several different types of lesions. The average performance, in terms of the area under the receiver-operating characteristic curve, reached 89.2 ± 0.9%. The best average performance was obtained for angiectasias (97.5 ± 2.4%) and nodular lymphangiectasias (96.3 ± 3.6%). LIMITATIONS: Single expert for annotation of pathologies, single type of WCE model, use of single images instead of entire WCE videos. CONCLUSION: A simple, yet effective, approach allowing automatic detection of all types of abnormalities in capsule endoscopy is presented. Based on color pattern recognition, it outperforms previous state-of-the-art approaches. Moreover, it is robust in the presence of luminal contents and is capable of detecting even very small lesions. Crown
BACKGROUND: The advent of wireless capsule endoscopy (WCE) has revolutionized the diagnostic approach to small-bowel disease. However, the task of reviewing WCE video sequences is laborious and time-consuming; software tools offering automated video analysis would enable a timelier and potentially a more accurate diagnosis. OBJECTIVE: To assess the validity of innovative, automatic lesion-detection software in WCE. DESIGN/INTERVENTION: A color feature-based pattern recognition methodology was devised and applied to the aforementioned image group. SETTING: This study was performed at the Royal Infirmary of Edinburgh, United Kingdom, and the Technological Educational Institute of Central Greece, Lamia, Greece. MATERIALS: A total of 137 deidentified WCE single images, 77 showing pathology and 60 normal images. RESULTS: The proposed methodology, unlike state-of-the-art approaches, is capable of detecting several different types of lesions. The average performance, in terms of the area under the receiver-operating characteristic curve, reached 89.2 ± 0.9%. The best average performance was obtained for angiectasias (97.5 ± 2.4%) and nodular lymphangiectasias (96.3 ± 3.6%). LIMITATIONS: Single expert for annotation of pathologies, single type of WCE model, use of single images instead of entire WCE videos. CONCLUSION: A simple, yet effective, approach allowing automatic detection of all types of abnormalities in capsule endoscopy is presented. Based on color pattern recognition, it outperforms previous state-of-the-art approaches. Moreover, it is robust in the presence of luminal contents and is capable of detecting even very small lesions. Crown
Authors: Vatsal Patel; Marium N Khan; Aman Shrivastava; Kamran Sadiq; S Asad Ali; Sean R Moore; Donald E Brown; Sana Syed Journal: J Pediatr Gastroenterol Nutr Date: 2020-01 Impact factor: 3.288