Background: Colonoscopy is the gold standard for polyp detection, but polyps may be missed. Artificial intelligence (AI) technologies may assist in polyp detection. To date, most studies for polyp detection have validated algorithms in ideal endoscopic conditions. Aim: To evaluate the performance of a deep-learning algorithm for polyp detection in a real-world setting of routine colonoscopy with variable bowel preparation quality. Methods: We performed a prospective, single-center study of 50 consecutive patients referred for colonoscopy. Procedural videos were analyzed by a validated deep-learning AI polyp detection software that labeled suspected polyps. Videos were then re-read by 5 experienced endoscopists to categorize all possible polyps identified by the endoscopist and/or AI, and to measure Boston Bowel Preparation Scale. Results: In total, 55 polyps were detected and removed by the endoscopist. The AI system identified 401 possible polyps. A total of 100 (24.9%) were categorized as “definite polyps;” 53/100 were identified and removed by the endoscopist. A total of 63 (15.6%) were categorized as “possible polyps” and were not removed by the endoscopist. In total, 238/401 were categorized as false positives. Two polyps identified by the endoscopist were missed by AI (false negatives). The sensitivity of AI for polyp detection was 98.8%, the positive predictive value was 40.6%. The polyp detection rate for the endoscopist was 62% versus 82% for the AI system. Mean segmental Boston Bowel Preparation Scale were similar (2.64, 2.59, P=0.47) for true and false positives, respectively. Conclusions: A deep-learning algorithm can function effectively to detect polyps in a prospectively collected series of colonoscopies, even in the setting of variable preparation quality.

Background and study aims Chemoradiation with stereotactic body radiation therapy (SBRT) is increasingly being used for optimal treatment of locally advanced pancreatobiliary cancers. Fiducial markers are used to track these tumors during SBRT. Endoscopic ultrasound (EUS) is the preferred route for fiducial marker placement for ease of access to pancreatobiliary structures and accurate placement. Here we evaluate the safety and infection risk associated with EUS-guided fiducial placement for pancreatobiliary malignancies and use of peri-procedural prophylactic antibiotics. Patients and methods This was a retrospective, single-center study including consecutive patients presenting for EUS-guided fiducial placement in pancreatobiliary region by three expert interventional endoscopists for SBRT from July 2010 to February 2018 at a tertiary care center. Patient demographics, tumor characteristics, EUS technique, fiducials, use of prophylactic antibiotics, adverse events (AEs) and SBRT/Cyberknife administration were reported. Results A total of 355 patients with pancreatobiliary malignancy underwent EUS-guided fiducial placement, of whom 308 patients (86.76 %) successfully underwent SBRT. Of the patients, 304 (85.63 %) received peri-procedural prophylactic antibiotic. Of 355 total patients, 5.9 % (n = 21) were noted to develop AEs (mild to severe) with no significant difference in incidence of infection with or without use of peri-procedural prophylactic antibiotic. Only three patients developed infectious AEs, none of which were definitively related to fiducial placement. Conclusion EUS-guided fiducial placement for pancreatobiliary malignancy is safe and efficacious, and risk of infection is rare, regardless of whether or not peri-procedural antibiotics are used. We favor limiting routine use of peri-procedural antibiotics for patients undergoing EUS-guided fiducial placement in pancreaticobiliary malignancy.