Usefulness of GI-GENIUS in FIT-based Colorectal Cancer Screening Program. (CADILLAC)

Usefulness of GI-GENIUS in FIT-based Colorectal Cancer Screening Program. Randomized Controlled Trial.

Deep learning technology has an increasing role in medical image applications and, recently, an artificial intelligence device has been developed and commercialized by Medtronic for identification of polyps during colonoscopy (GI-GENIUS). This kind of computer-aided detection (CADe) devices have demonstrated its ability for improving polyp detection rate (PDR) and the adenoma detection rate (ADR). However, this increase in PDR and ADR is mainly made at the expense of small polyps and non advanced adenomas. Colonoscopies after a positive fecal immunochemical test (FIT) could be the scenario with a higher prevalence of advanced lesions which could be the ideal situation for demonstrating if these CADe systems are able also to increase the detection of advanced lesions and which kind of advanced lesions are these systems able to detect. The CADILLAC study will randomize individuals within the population-based Spanish colorectal cancer screening program to receive a colonoscopy where the endoscopist is assisted by the GI-GENIUS device or to receive a standard colonoscopy. If our results are positive, that could suppose a big step forward for CADe devices, in terms of definitive demonstration of being of help for efectively identify also advanced lesions.

Colorectal Neoplasms, Intestinal Neoplasms, Gastrointestinal Neoplasms, Colonic Polyp, Colorectal Cancer, Adenoma Colon, Serrated Adenoma, Serrated Polyp

To determine the impact of the GI-GENIUS device as an assistant to the endoscopist to detect advanced lesions (advanced adenomas and advanced serrated polyps) in FIT-based screening colonoscopies.

To determine the ability of the GI-GENIUS device to detect other lesions (colorectal cancer, adenomas, advanced adenomas, serrated polyps, advanced serrated polyps, non-polypoid lesions ≥10mm and right-sided advanced adenomas)

To describe the characteristics of using the GI-GENIUS device during a colonoscopy: withdrawal time, false-positive and false-negative rate of advanced lesions using the device, etc.

Inclusion Criteria: Individuals with a positive result in fecal immunochemical test within the population-based colorectal cancer screening program. Complete colonoscopy with cecal intubation. Inform consent signed. Exclusion Criteria: Personal history of colorectal cancer. Family history of colorectal cancer: ≥2 FDR or ≥1 FDR diagnosed before 50 years of age. Family history of hereditary colorectal cancer syndromes: Lynch syndrome, FAP, etc. Personal history of inflammatory bowel disease. Terminal illness. Personal history of total proctocolectomy.

Aziz M, Fatima R, Dong C, Lee-Smith W, Nawras A. The impact of deep convolutional neural network-based artificial intelligence on colonoscopy outcomes: A systematic review with meta-analysis. J Gastroenterol Hepatol. 2020 Oct;35(10):1676-1683. doi: 10.1111/jgh.15070. Epub 2020 Apr 26.

Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F, Karnes W, Baldi P. Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. Gastroenterology. 2018 Oct;155(4):1069-1078.e8. doi: 10.1053/j.gastro.2018.06.037. Epub 2018 Jun 18.

Wang P, Berzin TM, Glissen Brown JR, Bharadwaj S, Becq A, Xiao X, Liu P, Li L, Song Y, Zhang D, Li Y, Xu G, Tu M, Liu X. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut. 2019 Oct;68(10):1813-1819. doi: 10.1136/gutjnl-2018-317500. Epub 2019 Feb 27.

Wang P, Liu X, Berzin TM, Glissen Brown JR, Liu P, Zhou C, Lei L, Li L, Guo Z, Lei S, Xiong F, Wang H, Song Y, Pan Y, Zhou G. Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study. Lancet Gastroenterol Hepatol. 2020 Apr;5(4):343-351. doi: 10.1016/S2468-1253(19)30411-X. Epub 2020 Jan 22. Erratum In: Lancet Gastroenterol Hepatol. 2020 Apr;5(4):e3.