Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study

Abstract

Background and aim: Optical diagnosis (OD) of colonic polyps is poorly reproducible outside high-volume referral centres. Present study aimed to assess whether real-time AI-assisted OD is accurate enough to implement the leave-in-situ strategy for diminutive (5mm) rectosigmoid (DRSPs) polyps. Methods: Consecutive colonoscopy outpatients with 5mm) rectosigmoid (DRSPs) polyps. Methods: Consecutive colonoscopy outpatients with >1 DRSP were included. DRSPs were categorized as adenomas or non-adenomas by the endoscopist, with different expertise in OD, with the assistance of real-time AI system (CADEYE, Fujifilm Co., Tokyo-Japan). Primary study endpoint was >90% negative predictive value (NPV) for adenomatous histology in high-confidence AI-assisted OD of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations (PIVI-1) threshold), with histopathology as reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (>90%, PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. Results: Overall 596 DRSPs were retrieved for histology in 389 patients; AI-assisted high-confidence OD was made in 92.3%. The NPV of AI-assisted OD for DRSPs (PIVI-1) was 91.0% (95%CI [87.1-93.9]%). PIVI-2 threshold was met in 97.4% (95%CI [95.7-98.9]%) and 92.6% (95%CI [90.0-95.2]%) of patients according to ESGE and USMSTF, respectively. The AI-assisted OD accuracy was significantly lower for non-experts (82.3%; 95% CI [76.4-87.3]%) than for experts (91.9%; 95%CI [88.5-94.5]%), however non-experts in OD quickly approached experts’ performances over time. Conclusion: AI-assisted OD matches the required PIVI thresholds. However, this does not offset the need for a high-level confidence and expertise by the endoscopist. The AI system seems to be useful especially for non-experts.

Current and future implications of artificial intelligence in colonoscopy

“…The other Italian clinical study [ 36 ] evaluated the performance of the CAD-EYE CADx module (Fujifilm, Japan), which delivers an optical diagnosis dynamically during live colonoscopy every time virtual chromoendoscopy is activated during the procedure. This system also provides a heat map of the area most likely to harbor the provided diagnosis.…”

Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

“…Two trials 114 115 from the same Japanese group, using a CADx system and employing endocytomicroscopy and NBI, showed conflicting results, the first concluding that the system could meet required thresholds, while the second, in a multicenter setting with less experienced endoscopists, failed to reach acceptable levels. Another single-center study 116 involving 162 patients with 544 polyps showed that an approved CADx system exceeded PIVI thresholds for implementation in clinical practice, while a multicenter experience 117 with another approved CADx system fell short of required thresholds.…”

Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists

“…These advances have already led to the introduction of the first commercially available, regulatory-approved CADx systems [6]. Although several of these CADx systems were able to reach the PIVI and SODA thresholds within prospective validation settings, none of the systems have yet been able to reach all performance thresholds [7][8][9][10][11]. In addition, there remain several limitations that might hamper widespread implementation of these systems in clinical practice [12].…”