Accuracy of polyp characterization by artificial intelligence and endoscopists: a prospective, non-randomized study in a tertiary endoscopy center.

Background and study aims Artificial intelligence (AI) in gastrointestinal endoscopy is developing very fast. Computer-aided detection of polyps and computer-aided diagnosis (CADx) for polyp characterization are available now. This study was performed to evaluate the diagnostic performance of a new commercially available CADx system in clinical practice. Patients and methods This prospective, non-randomized study was performed at a tertiary academic endoscopy center from March to August 2022. We included patients receiving a colonoscopy. Polypectomy had to be performed in all polyps. Every patient was examined concurrently by an endoscopist and AI using two opposing screens. The AI system, overseen by a second observer, was not visible to the endoscopist. The primary outcome was accuracy of the AI classifying the polyps into "neoplastic" and "non-neoplastic." The secondary outcome was accuracy of the classification by the endoscopists. Sessile serrated lesions were classified as neoplastic. Results We included 156 patients (mean age 65; 57 women) with 262 polyps ≤10 mm. Eighty-four were hyperplastic polyps (32.1%), 158 adenomas (60.3%), seven sessile serrated lesions (2.7%) and 13 other entities (normal/inflammatory colonmucosa, lymphoidic polyp) (4.9%) on histological diagnosis. Sensitivity, specificity and accuracy of AI were 89.70% (95% confidence interval [CI]: 84.02%-93.88%), 75.26% (95% CI: 65.46%-83.46%) and 84.35% (95% CI:79.38%-88.53%), respectively. Sensitivity, specificity and accuracy for less experienced endoscopists (2-5 years of endoscopy) were 95.56% (95% CI: 84.85%-99.46%), 61.54% (95% CI: 40.57%-79.77%) and 83.10% (95% CI: 72.34%-90.95%) and for experienced endoscopists 90.83% (95% CI: 84.19%-95.33%), 71.83% (95% CI: 59.90%-81.87%) and 83.77% (95% CI: 77.76%-88.70%), respectively. Conclusion Accuracy for polyp characterization by a new commercially available AI system is high, but does not fulfill the criteria for a "resect-and-discard" strategy.

Cystic pancreatic neoplasms in a tertiary gastroenterologic referral center: Evaluation of the diagnostic accuracy of endoscopic ultrasound, progression rate and malignancy rate in a large unicentric cohort.

INTRODUCTION: Cystic pancreatic neoplasms (CPN) are frequently diagnosed due to better diagnostic techniques and patients becoming older. However, diagnostic accuracy of endoscopic ultrasound (EUS) and value of follow-up are still unclear. MATERIAL AND METHODS: The aim of our retrospective study was to investigate the frequency of different cystic pancreatic neoplasms (intraductal papillary mucinous neoplasm [IPMN], serous and mucinous cystadenoma, solid pseudopapillary neoplasia), diagnostic accuracy, size progression, and rate of malignancy using EUS in a tertiary reference center in Germany. Between January 1, 2012 and December 31, 2018, 455 patients were diagnosed with cystic pancreatic lesions (798 EUS examinations). RESULTS: Endoscopic ultrasound diagnosed 223 patients with cystic pancreatic neoplasms, including 138 (61.9%) patients with branch duct IPMN, 16 (7.2%) with main duct IPMN, and five (2.2%) with mixed-type IPMN. In the largest subgroup of branch duct IPMN, cysts were size progressive in 20 patients (38.5%). Fine needle aspiration (FNA) was performed in 21 patients, and confirmed the suspected diagnosis in 12/21 patients. 28 surgical resections were performed, in 7/28 patients (25%), high-grade dysplasia or cancer was diagnosed. Endoscopic ultrasound diagnosis of serous and mucinous cystic pancreatic neoplasms was correct in 68.4%. CONCLUSIONS: Endoscopic ultrasound differential diagnosis of CPNs is challenging. Even in a tertiary expert center, differentiation of serous and mucinous cystic neoplasia is not guaranteed. Relevant size progression of CPN, however, is rare, as is the rate of malignancy. The data of this study suggest that morphologic criteria to assess pancreatic cysts alone are not sufficient to allow a clear diagnosis. Hence, for the improved assessment of pancreatic cysts, EUS should be combined with additional tests and techniques such as MRT/MRCP, contrast-enhanced EUS, and/or FNA/fine needle biopsy including fluid analysis. The combination and correlation of imaging studies with EUS findings is mandatory.

Diagnostic accuracy of a novel artificial intelligence system for adenoma detection in daily practice: a prospective nonrandomized comparative study.

BACKGROUND: Adenoma detection rate (ADR) varies significantly between endoscopists, with adenoma miss rates (AMRs) up to 26 %. Artificial intelligence (AI) systems may improve endoscopy quality and reduce the rate of interval cancer. We evaluated the efficacy of an AI system in real-time colonoscopy and its influence on AMR and ADR. METHODS: This prospective, nonrandomized, comparative study analyzed patients undergoing diagnostic colonoscopy at a single endoscopy center in Germany from June to October 2020. Every patient was examined concurrently by an endoscopist and AI using two opposing screens. The AI system, overseen by a second observer, was not visible to the endoscopist. AMR was the primary outcome. Both methods were compared using McNemar test. RESULTS: 150 patients were included (mean age 65 years [standard deviation 14]; 69 women). There was no significant or clinically relevant difference (P = 0.75) in AMR between the AI system (6/197, 3.0 %; 95 % confidence interval [CI] 1.1-6.5) and routine colonoscopy (4/197, 2.0 %; 95 %CI 0.6-5.1). The polyp miss rate of the AI system (14/311, 4.5 %; 95 %CI 2.5-7.4) was not significantly different (P = 0.72) from routine colonoscopy (17/311, 5.5 %; 95 %CI 3.2-8.6). There was no significant difference (P = 0.50) in ADR between routine colonoscopy (78/150, 52.0 %; 95 %CI 43.7-60.2) and the AI system (76/150, 50.7 %; 95 %CI 42.4-58.9). Routine colonoscopy detected adenomas in two patients that were missed by the AI system. CONCLUSION: The AI system performance was comparable to that of experienced endoscopists during real-time colonoscopy with similar high ADR (> 50 %).