← Issue №2/ week of Jul 12, 2026/Endoscopy

Artificial intelligence-assisted detection and optical differentiation of colorectal lesions in Lynch syndrome surveillance (CADLY2): a multicentre, open-label, randomised controlled superiority trial.

From GI Signals issue №2: what this paper found, what it changes, and where it sits against the current standard of care, reviewed by Simon Mathews, MD.

Endoscopy rct · Jul 16, 2026 · Lancet GH · IF 30.9

Artificial intelligence-assisted detection and optical differentiation of colorectal lesions in Lynch syndrome surveillance (CADLY2): a multicentre, open-label, randomised controlled superiority trial.

New evidenceartificial intelligencecolorectal cancer screeningLynch syndromecomputer-aided detection
Clinical takeawayConsider using AI-assisted colonoscopy (e.g., CAD EYE) for Lynch syndrome surveillance to improve adenoma detection, particularly in specialized hereditary cancer centers, acknowledging potential bias from unmasked endoscopists.
What it foundAI-assisted colonoscopy (CAD EYE) increased adenoma detection rate to 28% vs 19% with high-definition white-light (HD-WL) colonoscopy alone in Lynch syndrome surveillance.
ContextThis study provides new evidence supporting AI-assisted colonoscopy in Lynch syndrome surveillance, addressing prior sparse and inconsistent data in this high-risk population. Endoscopists were not masked, and safety outcomes were not detailed.
Measured against the standard of care· USMSTF 2020 (Gupta et al., post-polypectomy surveillance) / USMSTF 2026 (Rex et al., Serrated Polyposis Syndrome consensus statement)

Decision at stakethe use of standard colonoscopy for Lynch syndrome surveillance

… SPS colonoscopy should be done by endoscopists with documented adequate SSL detection, using high-definition white light with or without chromoendoscopy. … First-degree relatives start colonoscopy at age 40, or 10 years before the youngest CRC diagnosis in the family, or 5 years before the youngest SPS diagnosis, whichever comes first. …

From our summary of this standard, unedited — the part the paper bears on. … marks omitted text. Our wording, not the guideline's; read the source for its own text.

Our full summary of this standard

General post-polypectomy surveillance still follows USMSTF 2020 (Gupta et al.), which has not been replaced: 1-2 tubular adenomas <10 mm, 7-10 years; 3-4 tubular adenomas <10 mm, 3-5 years; 5-10 tubular adenomas <10 mm, any adenoma ≥10 mm, or an adenoma with tubulovillous/villous histology or high-grade dysplasia, 3 years; >10 adenomas, 1 year with polyposis evaluation. For serrated polyps: 1-2 SSLs <10 mm, 5-10 years; 3-4 SSLs <10 mm or a hyperplastic polyp ≥10 mm, 3-5 years; an SSL ≥10 mm, an SSL with dysplasia, or a traditional serrated adenoma, 3 years. When findings are mixed, use the shortest interval indicated. Before applying an interval, confirm complete resection and adequate prep. Piecemeal resections get a site check, and malignant (T1) polyps go to a tumor-board pathway. Serrated polyposis syndrome (SPS) is now governed by a separate USMSTF consensus statement (Rex et al., published simultaneously in Gastroenterology, Am J Gastroenterol and GIE on 2026-09-30). It has 11 recommendations. Diagnose SPS with the 2019 WHO criteria, which count the size, cumulative lifetime number and location of serrated polyps. Until SPS is diagnosed, record the number, size and location of serrated polyps in every colonoscopy report. SPS colonoscopy should be done by endoscopists with documented adequate SSL detection, using high-definition white light with or without chromoendoscopy. Without concurrent CRC, endoscopy is preferred over surgery for primary management. If the polyp burden cannot be managed endoscopically, refer to an advanced endoscopic resection expert before surgery. Resect SSLs and hyperplastic polyps by cold snare, with submucosal injection for larger lesions. Do clearance colonoscopy at 3-6 months, then surveil every 1-2 years. Consider 3-year intervals if the burden is greatly reduced at surveillance. First-degree relatives start colonoscopy at age 40, or 10 years before the youngest CRC diagnosis in the family, or 5 years before the youngest SPS diagnosis, whichever comes first. SPS has no established genetic basis, so germline testing is recommended only when concurrent non-serrated polyps suggest a heritable syndrome. Lynch, FAP/AFAP and MAP criteria still trigger genetic evaluation.

USMSTF 2020 (Gupta et al., post-polypectomy surveillance) / USMSTF 2026 (Rex et al., Serrated Polyposis Syndrome consensus statement) · reviewed 2026-10-11 ↗
Hüneburg R … CADLY2 investigators · Lancet Gastroenterology & Hepatology · IF 30.9 · PubMed ↗Permalink
← Read the whole of issue №2 Every paper GI Signals surfaces gets a page like this one. All issues