AI in colonoscopy - detection and characterisation of malignant polyps

Abstract

The medical technological revolution has transformed the nature with which we deliver care. Adjuncts such as artificial intelligence and machine learning have underpinned this. The applications to the field of endoscopy are numerous. Malignant polyps represent a significant diagnostic dilemma as they lie in an area in which mischaracterisation may mean the difference between an endoscopic procedure and a formal bowel resection. This has implications for patients’ oncological outcomes, morbidity and mortality, especially if post-procedure histopathology upstages disease. We have made significant strides with the applications of artificial intelligence to colonoscopic detection. Deep learning algorithms are able to be created from video and image databases. These have been applied to traditional, human-derived, classification methods, such as Paris or Kudo, with up to 93% accuracy. Furthermore, multimodal characterisation systems have been developed, which also factor in patient demographics and colonic location to provide an estimation of invasion and endoscopic resectability with over 90% accuracy. Although the technology is still evolving, and the lack of high-quality randomised controlled trials limits clinical usability, there is an exciting horizon upon us for artificial intelligence-augmented endoscopy.

Keywords

Colonoscopy / artificial intelligence / malignant polyps

References

[1] Sung H,Siegel RL.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.CA Cancer J Clin2021;71:209-49

[2] Cancer Research UK. Bowel cancer statistics. Available from: https://www.cancerresearchuk.org/health-professional/cancer-statistics/statistics-by-cancer-type/bowel-cancer. [Last accessed on 16 Sep 2023]

[3] Kader R,Georgiades F,Lovat LB.Optical diagnosis of colorectal polyps using convolutional neural networks.World J Gastroenterol2021;27:5908-18 PMCID:PMC8475008

[4] Shaukat A,Dominitz JA.Endoscopic recognition and management strategies for malignant colorectal polyps: recommendations of the US multi-society task force on colorectal cancer.Gastroenterology2020;159:1916-34.e2

[5] Sarma DP.The dukes classification of colorectal cancer.JAMA1986;256:1447

[6] Williams JG,Hill J.Management of the malignant colorectal polyp: ACPGBI position statement^†.Colorectal Dis2013;15:1-38

[7] Backes Y,ter Borg F.Multicentre prospective evaluation of real-time optical diagnosis of T1 colorectal cancer in large non-pedunculated colorectal polyps using narrow band imaging (the OPTICAL study).Gut2019;68:271-9

[8] Peery AF,Strassle PD.Increasing rates of surgery for patients with nonmalignant colorectal polyps in the United States.Gastroenterology2018;154:1352-60.e3 PMCID:PMC5880740

[9] Silver D,Simonyan K.Mastering the game of Go without human knowledge.Nature2017;550:354-9

[10] Ozturk T,Yildirim EA,Yildirim O.Automated detection of COVID-19 cases using deep neural networks with X-ray images.Comput Biol Med2020;121:103792 PMCID:PMC7187882

[11] Lee JG,Cho YW.Deep learning in medical imaging: general overview.Korean J Radiol2017;18:570-84 PMCID:PMC5447633

[12] Hosny A,Quackenbush J,Aerts HJWL.Artificial intelligence in radiology.Nat Rev Cancer2018;18:500-10 PMCID:PMC6268174

[13] Paeck KH,Park DI.Colonoscopy scheduling influences adenoma and polyp detection rates.Hepatogastroenterology2013;60:1647-52

[14] Glissen Brown JR,Wang P.Deep learning computer-aided polyp detection reduces adenoma miss rate: a United States multi-center randomized tandem colonoscopy study (CADeT-CS trial).Clin Gastroenterol Hepatol2022;20:1499-507.e4

[15] Wang P,Glissen Brown JR.Lower adenoma miss rate of computer-aided detection-assisted colonoscopy vs routine white-light colonoscopy in a prospective tandem study.Gastroenterology2020;159:1252-61.e5

[16] Wallace MB,Bhandari P.Impact of artificial intelligence on miss rate of colorectal neoplasia.Gastroenterology2022;163:295-304.e5

[17] Endoscopic Classification Review Group. Update on the paris classification of superficial neoplastic lesions in the digestive tract.Endoscopy2005;37:570-8

[18] Krenzer A,Fitting D. Automated classification of polyps using deep learning architectures and few-shot learning. Available from: https://doi.org/10.21203/rs.3.rs-2106189/v1. [Last accessed on 16 Sep 2023]

[19] Okamoto Y,Izakura S.Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions.J Gastroenterol Hepatol2022;37:104-10

[20] Ozawa T,Fujishiro M,Shichijo S.Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks.Therap Adv Gastroenterol2020;13:1756284820910659 PMCID:PMC7092386

[21] Kudo S,Nakajima T,Kusaka H.Diagnosis of colorectal tumorous lesions by magnifying endoscopy.Gastrointest Endosc1996;44:8-14

[22] Takemura Y,Tanaka S.Quantitative analysis and development of a computer-aided system for identification of regular pit patterns of colorectal lesions.Gastrointest Endosc2010;72:1047-51

[23] Patino-Barrientos S,Garcia-Zapirain B,Elmaghraby A.Kudo’s classification for colon polyps assessment using a deep learning approach.Appl Sci2020;10:501

[24] Lu Z,Yao L.Real-time automated diagnosis of colorectal cancer invasion depth using a deep learning model with multimodal data (with video).Gastrointest Endosc2022;95:1186-94.e3

[25] Yao L,Yang G.Development and validation of an artificial intelligence-based system for predicting colorectal cancer invasion depth using multi-modal data.Dig Endosc2023;35:625-35

[26] Karsenti D,Perrot B.Effect of real-time computer-aided detection of colorectal adenoma in routine colonoscopy (COLO-GENIUS): a single-centre randomised controlled trial.Lancet Gastroenterol Hepatol2023;8:726-34

[27] Levy I,Klang E,Kopylov U.Artificial intelligence-aided colonoscopy does not increase adenoma detection rate in routine clinical practice.Am J Gastroenterol2022;117:1871-3

[28] Ladabaum U,Weng Y,Singer SJ.Computer-aided detection of polyps does not improve colonoscopist performance in a pragmatic implementation trial.Gastroenterology2023;164:481-3.e6

[29] Kader R,Hussein M.Survey on the perceptions of UK gastroenterologists and endoscopists to artificial intelligence.Frontline Gastroenterol2022;13:423-9 PMCID:PMC9380773

[30] Fazal MI,Tye J.The past, present and future role of artificial intelligence in imaging.Eur J Radiol2018;105:246-50

[31] Antonelli G,Iacopini F.Current and future implications of artificial intelligence in colonoscopy.Ann Gastroenterol2023;36:114-22 PMCID:PMC9932855

[32] Bang CS,Baik GH.Computer-aided diagnosis of diminutive colorectal polyps in endoscopic images: systematic review and meta-analysis of diagnostic test accuracy.J Med Internet Res2021;23:e29682 PMCID:PMC8427459