AI-assisted selection of imaging mode in endoscopy

Abstract

Systems, devices, and methods for determining or adapting an imaging mode for use in examining tissue or foreign bodies during an endoscopic procedure are disclosed. An exemplary endoscopy system comprises an endoscope and a control circuit. The endoscope includes an imaging system for acquiring images or video data streams of a target anatomy during an endoscopic procedure. The control circuit can generate endoscopic image or video features from the acquired images or video data streams that characterize an anomaly in the target anatomy and determine a personalized, pathology-specific imaging mode to improve the detectability of the anomaly from the images or video data streams. The recommended imaging mode can be determined using a trained machine learning model.The recommended imaging mode can be provided to a user or process to facilitate manual or automatic adjustment of the endoscopic imaging mode during the endoscopic procedure.