Real-time Computer-Aided Detection of Colonic Adenomas With NEC WISE VISION® Endoscopy (COLOWISE)

Real-time Computer-Aided Detection of Colonic Adenomas With NEC WISE VISION® Endoscopy: Prospective, Randomized Clinical Performance Evaluation

This is a prospective, multicenter, randomized study to evaluate the clinical performance of a novel CADe device, WISE VISION® Endoscopy System, in patients undergoing high-definition white light (HDWL) colonoscopy for screening or surveillance of colorectal Cancer (CRC). Eligible subjects who meet the study inclusion/exclusion criteria will be randomized in a 1:1 ratio to undergo colonoscopy : Experimental: CADe colonoscopy procedure with WISE VISION® Endoscopy (CADe Group) Control: Standard Colonoscopy without CADe (Standard Colonoscopy Group)

This study aims to evaluate whether NEC WISE VISION® Endoscopy enhances the ability to detect mucosal lesions when compared with the current standard-of-care procedure (high-definition white light [HDWL] colonoscopy). The CADe device, Wise VISION® Endoscopy, contains an artificial intelligence/machine learning (AI/ML) advanced algorithm to aid the endoscopists in detection of colonic lesions. This study plans to enrol 700 subjects aged ≥ 45 years and < 75 years, who are scheduled for screening or surveillance colonoscopy. After review of the inclusion and exclusion criteria, eligible subjects will be randomized in a 1:1 ratio to receive either computer-aided colonoscopy (CADe Group) or standard colonoscopy without CADe (Standard Colonoscopy Group). All adenomas, that are identified during the colonoscopies, will be removed and biopsied as per standard clinical practice to assess adenoma miss rate, polyp miss rate, adenomas per colonoscopy and other endpoints.

Computer-aided detection (CADe) devices are used in conjunction with colonoscopy to aid in the detection of lesions in the gastrointestinal tract.

Total number of histologically confirmed adenomas resected divided by the total number of colonoscopies.

Inclusion Criteria: Patient is presenting to the endoscopy unit for colon cancer screening or surveillance colonoscopy. Signed Informed Consent Exclusion Criteria: Contraindications to colonoscopy Colonoscopy within the previous three (3) years High-risk indications for colonoscopy Antithrombotic therapy that cannot be stopped, precluding polyp resection Inflammatory bowel disease Referred for endoscopic mucosal resection (EMR) Familial adenomatous polyposis syndrome or Serrated Polyposis Syndrome Pregnant or planning a pregnancy during the study period

Yamada M, Saito Y, Imaoka H, Saiko M, Yamada S, Kondo H, Takamaru H, Sakamoto T, Sese J, Kuchiba A, Shibata T, Hamamoto R. Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy. Sci Rep. 2019 Oct 8;9(1):14465. doi: 10.1038/s41598-019-50567-5.