Background & Aims: Artificial intelligence (AI)-based optical diagnosis systems (CADx) have been developed to allow pathology prediction of colorectal polyps during colonoscopies. However, CADx systems have not yet been validated for autonomous performance. Therefore, we conducted a trial comparing autonomous AI to AI-assisted human (AI-H) optical diagnosis.
View Article and Find Full Text PDFAn independent observer can improve procedural quality. We evaluated the impact of the observer (Hawthorne effect) on important quality metrics during colonoscopies. In a single-center comparative study, consecutive patients undergoing routine screening or diagnostic colonoscopy were prospectively enrolled.
View Article and Find Full Text PDFIntroduction: Serrated lesions (SLs) including traditional serrated adenomas (TSA), large hyperplastic polyps (HP) and sessile serrated lesions (SSLs) are associated with high incomplete resection rates. Margin ablation combined with EMR (EMR-T) has become routine to reduce local recurrence while cold snare polypectomy (CSP) is becoming recognized as equally effective for large SLs. Our aim was to evaluate local recurrence rates (LRR) and the use of margin ablation in preventing recurrence in a retrospective cohort study.
View Article and Find Full Text PDFBackground And Aims: Identification and photo-documentation of the ileocecal valve (ICV) and appendiceal orifice (AO) confirm completeness of colonoscopy examinations. We aimed to develop and test a deep convolutional neural network (DCNN) model that can automatically identify ICV and AO, and differentiate these landmarks from normal mucosa and colorectal polyps.
Methods: We prospectively collected annotated full-length colonoscopy videos of 318 patients undergoing outpatient colonoscopies.