Copyright ©The Author(s) 2020.
World J Gastroenterol. Dec 14, 2020; 26(46): 7287-7298
Published online Dec 14, 2020. doi: 10.3748/wjg.v26.i46.7287
Table 1 Recent clinical studies in artificial intelligence using central neural network and capsule endoscopy for small intestinal imaging
Type of study
Aim of study
Aoki et al[58], 2020RetrospectiveDetection of mucosal breaks/erosion20 capsule endoscopy videosDetection rate, expert 87%; trainee, 55%
Klang et al[59], 2020RetrospectiveDetection of small intestinal ulcers in Crohn’s disease17640 images from 49 patientsAccuracy, 96.7%; sensitivity, 96.8%; specificity, 96.6% (5-fold)
Tsuboi et al[60], 2020RetrospectiveDetection of small intestinal angiodysplasia2237 images from 141 patientsSensitivity, 98.8%; specificity, 98.4%
Ding et al[61], 2019RetrospectiveDetection of small intestinal abnormal images158235 images from 1970 patientsSensitivity, 99.9%; reading time, 5.9 min
Saito et al[62], 2020RetrospectiveDetection and classification of protruding lesions30584 images from 292 patientsSensitivity, 90.7%; specificity, 79.8%; reading time, 530.462 s