Jochen Weigt1, Alessandro Repici2,3, Giulio Antonelli4, Ahmed Afifi1, Leon Kliegis1, Loredana Correale2, Cesare Hassan4, Helmut Neumann5,6. 1. Department of Gastroenterology, Hepatology and Infectious Diseases, Otto-v. Guericke University, Magdeburg, Germany. 2. Endoscopy Unit, Humanitas Clinical and Research Center - IRCCS, Milan, Italy. 3. Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy. 4. Gastroenterology Unit, Nuovo Regina Margherita Hospital, Rome, Italy. 5. Department of Interdisciplinary Endoscopy, University Hospital Mainz, Mainz, Germany. 6. GastroZentrum Lippe, Interventional Endoscopy, Bad Salzuflen, Germany.
Abstract
BACKGROUND: Use of artificial intelligence may increase detection of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe) and reduce pathology costs by improving optical diagnosis (CADx). METHODS: A multicenter library of ≥ 200 000 images from 1572 polyps was used to train a combined CADe/CADx system. System testing was performed on two independent image sets (CADe: 446 with polyps, 234 without; CADx: 267) from 234 polyps, which were also evaluated by six endoscopists (three experts, three non-experts). RESULTS: CADe showed sensitivity, specificity, and accuracy of 92.9 %, 90.6 %, and 91.7 %, respectively. Experts showed significantly higher accuracy and specificity, and similar sensitivity, while non-experts + CADe showed comparable sensitivity but lower specificity and accuracy than CADe and experts. CADx showed sensitivity, specificity, and accuracy of 85.0 %, 79.4 %, and 83.6 %, respectively. Experts showed comparable performance, whereas non-experts + CADx showed comparable accuracy but lower specificity than CADx and experts. CONCLUSIONS: The high accuracy shown by CADe and CADx was similar to that of experts, supporting further evaluation in a clinical setting. When using CAD, non-experts achieved a similar performance to experts, with suboptimal specificity. Thieme. All rights reserved.
BACKGROUND: Use of artificial intelligence may increase detection of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe) and reduce pathology costs by improving optical diagnosis (CADx). METHODS: A multicenter library of ≥ 200 000 images from 1572 polyps was used to train a combined CADe/CADx system. System testing was performed on two independent image sets (CADe: 446 with polyps, 234 without; CADx: 267) from 234 polyps, which were also evaluated by six endoscopists (three experts, three non-experts). RESULTS: CADe showed sensitivity, specificity, and accuracy of 92.9 %, 90.6 %, and 91.7 %, respectively. Experts showed significantly higher accuracy and specificity, and similar sensitivity, while non-experts + CADe showed comparable sensitivity but lower specificity and accuracy than CADe and experts. CADx showed sensitivity, specificity, and accuracy of 85.0 %, 79.4 %, and 83.6 %, respectively. Experts showed comparable performance, whereas non-experts + CADx showed comparable accuracy but lower specificity than CADx and experts. CONCLUSIONS: The high accuracy shown by CADe and CADx was similar to that of experts, supporting further evaluation in a clinical setting. When using CAD, non-experts achieved a similar performance to experts, with suboptimal specificity. Thieme. All rights reserved.
Authors: Markus Brand; Joel Troya; Adrian Krenzer; Zita Saßmannshausen; Wolfram G Zoller; Alexander Meining; Thomas J Lux; Alexander Hann Journal: United European Gastroenterol J Date: 2022-05-05 Impact factor: 6.866
Authors: Quirine E W van der Zander; Mirjam C M van der Ende-van Loon; Janneke M M Janssen; Bjorn Winkens; Fons van der Sommen; Ad A M Masclee; Erik J Schoon Journal: Sci Rep Date: 2022-10-06 Impact factor: 4.996
Authors: Joel Troya; Daniel Fitting; Markus Brand; Boban Sudarevic; Jakob Nikolas Kather; Alexander Meining; Alexander Hann Journal: Endoscopy Date: 2022-02-14 Impact factor: 9.776