Colorectal cancer (CRC) prevention depends on effective colonoscopy; yet variability in adenoma detection rates (ADRs) and missed lesions remain significant hurdles. Artificial intelligence-powered computer-aided detection (CADe) systems offer promising advancements in enhancing polyp detection. This review examines the role of CADe in improving ADR and reducing adenoma miss rates (AMRs) while addressing its broader clinical implications. CADe has demonstrated consistent improvements in ADRs and AMRs; largely by detecting diminutive polyps, but shows limited efficacy in identifying advanced adenomas or sessile serrated lesions. Challenges such as operator deskilling and the need for enhanced algorithms persist. Combining CADe with adjunctive techniques has shown potential for further optimizing performance. While CADe has standardized detection quality; its long-term impact on CRC incidence and mortality remains inconclusive. Future research should focus on refining CADe technology and assessing its effectiveness in reducing the global burden of CRC.
Endoscopic submucosal dissection (ESD) is the standard of care for the en bloc resection of large colorectal lesions but remains technically demanding, with long procedure times, a steep learning curve, and complication rates that have constrained adoption outside expert Eastern centres. Undersaline ESD (UESD) has emerged as a modification in which gas insufflation is replaced by immersion in isotonic saline, exploiting the distinct physical properties of a liquid-filled lumen to address several limitations of the conventional technique. Although frequently described as “underwater” ESD, the term “undersaline ESD” is more precise, since its advantages derive specifically from the ionic content of saline rather than from submersion alone. This narrative review synthesises the mechanistic rationale and the accumulating clinical evidence on UESD for large colorectal lesions. Saline immersion alters monopolar electrosurgical behaviour towards a coagulation-dominant profile, generates intrinsic traction on the mucosal flap through differential buoyancy, magnifies the dissection plane, and dissipates thermal energy. Across observational series and two recent meta-analyses, UESD is associated with faster submucosal dissection without compromising en bloc resection, R0 resection or short-term safety. The randomised evidence is not uniform: two of three trials reported faster dissection, while the largest found no difference in its primary endpoint, with lesion position determining the relative advantage of each technique. The benefits appear concentrated in specific settings such as submucosal fibrosis, gravity-side lesions, and, on preliminary data, non-expert operators, rather than distributed across all procedures. Key evidence gaps include the East Asian concentration of randomised data, the heterogeneity of technical implementation, and an absence of long-term oncological outcomes.