TY - JOUR
T1 - Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions
T2 - a real-time comparison with screening endoscopists
AU - Houwen, Britt B. S. L.
AU - Hazewinkel, Yark
AU - Giotis, Ioannis
AU - Vleugels, Jasper L. A.
AU - Mostafavi, Nahid S.
AU - van Putten, Paul
AU - Fockens, Paul
AU - POLAR study group
AU - Dekker, Evelien
N1 - Funding Information: ED received a research grant from Fujifilm, a consulting fee for medical advice from Olympus, Fujifilm, GI Supply, PAION, Ambu and CPP-FAP and a speakers' fee from Olympus, Roche, GI Supply, Norgine, Fujifilm and IPSEN. PF received research support from Boston Scientific and a consulting fee from Olympus and Cook Endoscopy. The remaining Authors declare that there is no conflict of interest. Publisher Copyright: © 2022 Georg Thieme Verlag. All rights reserved.
PY - 2023/8/1
Y1 - 2023/8/1
N2 - BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.
AB - BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85166362440&origin=inward
UR - https://www.ncbi.nlm.nih.gov/pubmed/36623839
UR - http://www.scopus.com/inward/record.url?scp=85159687859&partnerID=8YFLogxK
U2 - https://doi.org/10.1055/a-2009-3990
DO - https://doi.org/10.1055/a-2009-3990
M3 - Article
C2 - 36623839
SN - 0013-726X
VL - 55
SP - 756
EP - 765
JO - Endoscopy
JF - Endoscopy
IS - 8
ER -