A medical decision support system using an artificial intelligence module for endoscopic examination of the stomach

The use of deep machine learning methods and algorithms to solve the problem of automatic detection and classification of oncological pathologies on endoscopic video images of the stomach was analyzed. A database of endoscopic images of the stomach has been compiled and contains more than 14,000 images, divided into three classes: “cancer,” “early cancer,” and “other pathology.” A prototype medical decision support system for endoscopy has been developed, consisting of separate modules each with its own complete functionality.