O53 AI-assisted detection-characterization-sizing of colorectal polyps. Can AI support non-expert endoscopists to achieve PIVI thresholds?

• Published in: Gut Vol. 71; no. Suppl 1; pp. A30 - A31
• Main Authors: Abdelrahim, Mohamed, Takoh, Kimiyasu, Okuno, Takayuki, Goda, Shimpei, Htet, Hein, Hamson, Joe, Aslam, Shahila, Siggens, Katie, Tanasescu, Andrea, Nair, Sujith Sasidharan, Elias, Mary, Salviato, Antonio, Mohammed, Salma, Parra-Blanco, Adolfo, Ishaq, Sauid, Antonelli, Giulio, Fraile-López, Miguel, Spadaccini, Marco, Subramaniam, Sharmila, Longcroft-Wheaton, Gaius, Alkandari, Asma, Hassan, Cesare, Repici, Alessandro, Bhandari, Pradeep
• Format: Journal Article
• Language: English
• Published: London BMJ Publishing Group Ltd and British Society of Gastroenterology 19.06.2022; BMJ Publishing Group LTD
• Subjects: Decision making; Endoscopy; Oral presentations; Polyps
• ISSN: 0017-5749; 1468-3288
• DOI: 10.1136/gutjnl-2022-BSG.53

IntroductionReal-time in-vivo characterisation of colorectal polyps remains limited outside expert centres. Data on AI polyp detection and characterisation is promising but accurate sizing remains the missing jigsaw piece. We aimed to study the impact of a novel AI system on non-expert endoscopists detection, characterisation and sizing of colorectal polyps compared to experts.MethodsProspectively collected endoscopy videos from twelve centres in Europe and Japan were uploaded on a bespoke online platform. All polyps were histologically proven and sized by three experts. The AI model detects polyps and classifies them as neoplastic/non-neoplastic and diminutive/non-diminutive. We asked Six experts to detect, characterise and size polyps without AI support, and Six non-experts to detect polyps assisted by AI, and to characterise and size polyps without and then with AI.Results199 videos (100-polyps) were included. On polyp detection, average sensitivity and specificity of non-experts +AI compared to experts was 96.0% and 84.6% compared to 95.7% and 89.9% respectively (p>0.5). Non-experts+AI showed superior sensitivity (95.5% vs 83.3%) and NPV (90.8% vs 70.4%) of characterisation on enhanced imaging compared to non-experts alone (p<0.5). On sizing, non-experts+AI achieved accuracy and sensitivity of 84.0% and 93.6%, respectively. Experts’ characterisation and sizing metrics were not significantly different from non-experts+AI.Abstract O53 Table 1Summary of the performance of non-expert endoscopists assisted by AI compared to experts (n=199 videos, 100 polyps) Metric Non experts +AI Experts P value Sensitivity of polyp detection 96.0% 95.7% >0.5 Sensitivity of characterisation on EI 95.5% 92.4% >0.5 NPV of characterisation on EI 90.8% 86.7% >0.5 Sensitivity of sizing 93.6% 92.2% >0.5 NPV of sizing 93.1% 92.3% >0.5 Abstract O53 Figure 1The AI system detects polyps in real-time and classify them with high accuracy as either neoplastic or neoplastic, and diminutive or non-diminutive, thus assisting endoscopists with decision making in real-time fashionConclusionThis interim analysis suggests our AI system may support non-experts to perform at experts’ level and achieve PIVI-2 threshold (diagnose and leave). Further analysis is underway to understand the impact of the AI system on surveillance interval (PIVI-1). To our knowledge, this is the first report incorporating AI-assisted sizing with detection and characterisation.