This MEDTEQ initiative is converging surgical & artificial intelligence (“AI”) expertise, to advance the future of endoscopic procedures with deep learning (“DL”). Particularly, we are dedicated to contributing to the field of Gastroenterology, that requires physicians to perform a myriad of clinical skills, ranging from dexterous manipulation and navigation of endoscopic devices to visual identification and classification of disease, the latter being amenable to data-driven clinical decision-making. Specifically, we have elected to start in diagnostic imaging applied to colorectal cancer (“CRC”) screening, that has allowed for a reduction in the incidence and mortality of CRC via the detection and removal of adenomatous polyps. Yet, the effect of colonoscopy on CRC mortality is limited by several factors, among them a certain miss rate, leading to limited adenoma detection rates (“ADR”). We aim at a real-time automatic polyp detection system, with performance close to that of expert endoscopists for ADR, to assist in detecting lesions that might correspond to adenomas in a more consistent and reliable way. Furthermore, this project aim at extending the detection of polyp to the prediction of lesion histology, including differentiation of precancerous lesions from non-neoplastic lesions, and potentially the prediction of deep submucosal invasion of cancer.