Computer-aided detection in real-world colonoscopy: enhancing detection or offering false hope?

Abstract

Colorectal cancer stands as the second leading cause of cancer-related deaths worldwide, posing an important global health challenge. Screening colonoscopy with removal of neoplastic lesions has been recognised as one of the most effective methods of preventing colorectal cancer. 1 Zauber AG Winawer SJ O'Brien MJ et al. Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med. 2012; 366: 687-696 Crossref PubMed Scopus (2095) Google Scholar Adenoma detection rate (ADR) serves as a crucial quality indicator in colonoscopy, as it is inversely associated with post-colonoscopy (interval) colorectal cancer. 2 Kaminski MF Regula J Kraszewska E et al. Quality indicators for colonoscopy and the risk of interval cancer. N Engl J Med. 2010; 362: 1795-1803 Crossref PubMed Scopus (1431) Google Scholar However, it is estimated that around a quarter of colorectal neoplasms are missed during a single colonoscopy procedure. 3 van Rijn JC Reitsma JB Stoker J Bossuyt PM van Deventer SJ Dekker E Polyp miss rate determined by tandem colonoscopy: a systematic review. Am J Gastroenterol. 2006; 101: 343-350 Crossref PubMed Scopus (1056) Google Scholar To address this issue, computer-aided detection (CADe) systems using artificial intelligence (AI) have emerged as promising tools that allow increased detection of colorectal neoplastic lesions, thus enhancing the overall effectiveness of colonoscopy. 4 Misawa M Kudo SE Mori Y et al. Current status and future perspective on artificial intelligence for lower endoscopy. Dig Endosc. 2021; 33: 273-284 Crossref PubMed Scopus (16) Google Scholar Effect of real-time computer-aided detection of colorectal adenoma in routine colonoscopy (COLO-GENIUS): a single-centre randomised controlled trialOur findings support the benefits of CADe, even in a non-academic centre. Systematic use of CADe in routine colonoscopy should be considered. Full-Text PDF