Computer-aided detection (CADe) techniques based on artificial intelligence (AI) algorithms had higher detection rates of colorectal neoplasia compared with other techniques such as chromoendoscopy or tools that increase mucosal visualization. These findings were published in The Lancet Gastroenterology and Hepatology.
CADe ranked as the superior strategy for the detection of adenomas and was deemed the most promising technique compared with alternative strategies that aim to increase the contrast for neoplasia detection or the coverage of the whole mucosal surface.
Although novel techniques based on AI algorithms have been developed to improve the detection of colorectal lesions, the utility of CADe compared with existing advanced imaging techniques and distal attachment devices is ambiguous.
There are no randomized controlled trials directly comparing the effectiveness of CADe systems with other advanced endoscopy imaging techniques for the detection of colorectal neoplasia.
In a systematic review and network meta-analysis, researchers compared the effectiveness of CADe with various competing endoscopic techniques used for the detection of colorectal neoplasia.
The meta-analysis included 50 randomized controlled trials enabling simultaneous comparison of CADe (6 trials), chromoendoscopy (18 trials), and increased mucosal visualization systems (26 trials) and included 34,445 participants in total. In all 50 studies, high-definition (HD) white-light endoscopy was used as the control technique.
As compared with the control technique, the adenoma detection rate was 7.4% higher with CADe (odds ratio [OR], 1.78; 95% CI, 1.44-2.18), 4.4% higher with chromoendoscopy (OR, 1.22; 95% CI, 1.08-1.39), and 4.1% higher with increased mucosal visualization systems (OR, 1.16; 95% CI, 1.04-1.28).
CADe showed a significant increase in the adenoma detection rate when compared with increased mucosal visualization systems (OR, 1.54; 95% CI, 1.22-1.94; low certainty of evidence) and with chromoendoscopy (OR, 1.45; 95% CI, 1.14-1.85; moderate certainty of evidence).
A significant increase in the detection of large adenomas (≥10 mm) was also reported only with CADe (OR, 1.69; 95% CI, 1.10-2.60, moderate certainty of evidence) when compared with HD white-light endoscopy.
CADe also appeared to be the superior technique for the detection of sessile serrated lesions (with moderate confidence in hierarchical ranking). However, there was no significant increase in the sessile serrated lesion detection rate with CADe (OR, 1.37; 95% CI, 0.65-2.88).
HD white-light endoscopy was rated as the superior endoscopic technique for withdrawal time, while chromoendoscopy was found to be the worst technique. Withdrawal time was longer with chromoendoscopy compared with HD white-light endoscopy (mean difference, 0.66 min; 95% CI, 0.17-1.16).
“CADe seems to have an advantage over other advanced endoscopy imaging techniques, such as chromoendoscopy or mucosal visualization tools, for increasing the detection of colorectal neoplasia, which supports wider incorporation of CADe technologies into community endoscopy services,” the authors wrote.
Disclosure: Some study authors declared affiliations with biotech, pharmaceutical, and/or device companies. Please see the original reference for a full list of disclosures.
Spadaccini M, Iannone A, Maselli R, et al. Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: A systematic review and network meta-analysis. Lancet Gastroenterol Hepatol. Published online August 4, 2021. doi:10.1016/S2468-1253(21)00215-6