Dataset Information

A novel AI device for real-time optical characterization of colorectal polyps.

ABSTRACT: Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conventional white light (WL) endoscopy video stream without virtual chromoendoscopy (blue light, BL). In this work, we evaluated the standalone performance of this computer-aided diagnosis device (CADx) on a prospectively acquired dataset of unaltered colonoscopy videos. An international group of endoscopists performed optical characterization of each polyp acquired in a prospective study, blinded to both histology and CADx result, by means of an online platform enabling careful video assessment. Colorectal polyps were categorized by reviewers, subdivided into 10 experts and 11 non-experts endoscopists, and by the CADx as either "adenoma" or "non-adenoma". A total of 513 polyps from 165 patients were assessed. CADx accuracy in WL was found comparable to the accuracy of expert endoscopists (CADx_WL/Exp; OR 1.211 [0.766-1.915]) using histopathology as the reference standard. Moreover, CADx accuracy in WL was found superior to the accuracy of non-expert endoscopists (CADx_WL/NonExp; OR 1.875 [1.191-2.953]), and CADx accuracy in BL was found comparable to it (CADx_BL/CADx_WL; OR 0.886 [0.612-1.282]). The proposed intelligent device shows the potential to support non-expert endoscopists in systematically reaching the performances of expert endoscopists in optical characterization.

SUBMITTER: Biffi C

PROVIDER: S-EPMC9247164 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description: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.

Project description:Background and study aims Correct optical diagnosis of colorectal polyps is crucial to implement a resect and discard strategy. Training methods have been proposed to reach recommended optical diagnosis thresholds. The aim of our study was to present a systematic review and meta-analysis on optical diagnosis training. Methods PubMed/Medline and Cochrane databases were searched between 1980 and October 2019 for studies reporting outcomes on optical diagnosis training of colorectal polyps. The primary outcome was optical diagnosis accuracy compared to histological analysis pre-training and post-training intervention. Subgroup analyses of experienced/trainee endoscopists, training methods, and small/diminutive polyps were included. Results Overall, 16 studies met inclusion criteria, analyzing the impact of training on 179 endoscopists. Pre-training accuracy was 70.3 % (6416/9131 correct diagnoses) whereas post-training accuracy was 81.6 % (7416/9213 correct diagnoses) (risk ratio [RR] 1.17; 95 % confidence interval [CI]: 1.09-1.24, P < 0.001). In experienced endoscopists, accuracy improved from 69.8 % (3771/5403 correct diagnoses) to 82.4 % (4521/5485 correct diagnoses) (RR 1.20; 95 % CI: 1.11-1.29, P < 0.001). Among trainees, accuracy improved from 69.6 % (2645/3803 correct diagnoses) to 78.8 % (2995/3803 correct diagnoses) (RR 1.14; 95 % CI 1.06-1.24, P < 0.001). In the small/diminutive polyp subgroup, accuracy improved from 68.1 % (3549/5214 correct diagnoses) to 77.1 % (4022/5214 correct diagnoses) in (RR 1.16 95 % CI 1.08-1.24 P < 0.001). On meta-regression analysis, the improvement in accuracy did not differ between computerized vs. didactic training approaches for experienced ( P = 0.792) and trainee endoscopists ( P = 0.312). Conclusions Optical diagnosis training is effective in improving accuracy of histology prediction in colorectal polyps. Didactic and computer-based training show comparable effectiveness in improving diagnostic accuracy.

Dataset Information

A novel AI device for real-time optical characterization of colorectal polyps.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets