Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists

Abstract

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.

• References

• 1 Vleugels JLA, Greuter MJE, Hazewinkel Y. et al. Implementation of an optical diagnosis strategy saves costs and does not impair clinical outcomes of a fecal immunochemical test-based colorectal cancer screening program. Endosc Int Open 2017; 5: E1197-E1207
• 2 Hewett DG, Kaltenbach T, Sano Y. et al. Validation of a simple classification system for endoscopic diagnosis of small colorectal polyps using narrow-band imaging. Gastroenterology 2012; 143: 599-607
• 3 Houwen B, Hassan C, Coupé VMH. et al. Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy 2022; 54: 88-99
• 4 Rex DK, Kahi C, O’Brien M. et al. The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps. Gastrointest Endosc 2011; 73: 419-422
• 5 Ahmad OF, Soares AS, Mazomenos E. et al. Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. Lancet Gastroenterol Hepatol 2019; 4: 71-80
• 6 Taghiakbari M, Mori Y, von Renteln D. Artificial intelligence-assisted colonoscopy: a review of current state of practice and research. World J Gastroenterol 2021; 27: 8103-8122
• 7 Minegishi Y, Kudo SE, Miyata Y. et al. Comprehensive diagnostic performance of real-time characterization of colorectal lesions using an artificial intelligence-assisted system: a prospective study. Gastroenterology 2022; 163: 323-325
• 8 Hassan C, Balsamo G, Lorenzetti R. et al. Artificial intelligence allows leaving-in-situ colorectal polyps. Clin Gastroenterol Hepatol 2022; 20: 2505-2513
• 9 Rondonotti E, Hassan C, Tamanini G. et al. Artificial intelligence assisted optical diagnosis for resect and discard strategy in clinical practice (Artificial intelligence BLI Characterization; ABC study). Endoscopy 2023; 55: 14-22
• 10 Barua I, Wieszczy P, Kudo SE. et al. Real-time artificial intelligence-based optical diagnosis of neoplastic polyps during colonoscopy. NEJM Evid 2022; 1: EVIDoa2200003
• 11 Mori Y, Kudo SE, Misawa M. et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann Intern Med 2018; 169: 357-366
• 12 Parsa N, Byrne MF. Artificial intelligence for identification and characterization of colonic polyps. Ther Adv Gastrointest Endosc 2021; 14
• 13 Snover DC. Update on the serrated pathway to colorectal carcinoma. Hum Pathol 2011; 42: 1-10
• 14 Toes-Zoutendijk E, van Leerdam ME, Dekker E. et al. Real-time monitoring of results during first year of dutch colorectal cancer screening program and optimization by altering fecal immunochemical test cut-off levels. Gastroenterology 2017; 152: 767-775
• 15 Binefa G, Garcia M, Milà N. et al. Colorectal cancer screening programme in Spain: results of key performance indicators after five rounds (2000–2012). Sci Rep 2016; 6: 19532
• 16 Bossuyt PM, Reitsma JB, Bruns DE. et al. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ 2015; 351: h5527
• 17 Lin TY, Maire M, Belongie S. et al. Microsoft COCO: common objects in context. Fleet D, Pajdla T, Schiele B, Tuytelaars T. Computer Vision – ECCV 2014. Cham: Springer; 2014. (Lecture Notes in Computer Science; 8693). 740-755
• 18 Bochkovskiy A, Wang CY, Liao HYM. Yolov4: optimal speed and accuracy of object detection. arXiv preprint 2020; 2004.10934v1
• 19 Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis 2004; 60: 91-110
• 20 Nowak E, Jurie F, Triggs B. Sampling strategies for bag-of-features image classification. Leonardis A, Bischof H, Pinz A. Computer Vision – ECCV 2006. Berlin, Heidelberg: Springer; 2006. (Lecture Notes in Computer Science; 3954). 490-503
• 21 Rees CJ, Rajasekhar PT, Wilson A. et al. Narrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study. Gut 2017; 66: 887-895
• 22 Vleugels JLA, Dijkgraaf MGW, Hazewinkel Y. et al. Effects of training and feedback on accuracy of predicting rectosigmoid neoplastic lesions and selection of surveillance intervals by endoscopists performing optical diagnosis of diminutive polyps. Gastroenterology 2018; 154: 1682-1693
• 23 The Paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon: November 30 to December 1, 2002. Gastrointest Endosc 2003; 58 (Suppl. 06): S3–43
• 24 World Health Organization classification of tumours. Pathology and genetics of tumours of the digestive system. Hamilton SR, Aaltonen LA. Lyon: IARC Press; 2000
• 25 IJspeert JEG, Madani A, Overbeek LIH. et al. Implementation of an e-learning module improves consistency in the histopathological diagnosis of sessile serrated lesions within a nationwide population screening programme. Histopathology 2017; 70: 929-937
• 26 Chen PJ, Lin MC, Lai MJ. et al. Accurate classification of diminutive colorectal polyps using computer-aided analysis. Gastroenterology 2018; 154: 568-575
• 27 van der Sommen F, de Groof J, Struyvenberg M. et al. Machine learning in GI endoscopy: practical guidance in how to interpret a novel field. Gut 2020; 69: 2035-2045
• 28 Zachariah R, Samarasena J, Luba D. et al. Prediction of polyp pathology using convolutional neural networks achieves "resect and discard" thresholds. Am J Gastroenterol 2020; 115: 138-144
• 29 Zorron Cheng Tao Pu L, Maicas G, Tian Y. et al. Computer-aided diagnosis for characterization of colorectal lesions: comprehensive software that includes differentiation of serrated lesions. Gastrointest Endosc 2020; 92: 891-899
• 30 Leggett B, Whitehall V. Role of the serrated pathway in colorectal cancer pathogenesis. Gastroenterology 2010; 138: 2088-2100
• 31 van Putten PG, Hol L, van Dekken H. et al. Inter-observer variation in the histological diagnosis of polyps in colorectal cancer screening. Histopathology 2011; 58: 974-981
• 32 Sanchez-Montes C, Sanchez FJ, Bernal J. et al. Computer-aided prediction of polyp histology on white light colonoscopy using surface pattern analysis. Endoscopy 2019; 51: 261-265
• 33 Komeda Y, Handa H, Watanabe T. et al. Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification: preliminary experience. Oncology 2017; 93 (Suppl. 01) 30-34