The article proposed and built a tomographic and X-ray recognition system for the search and localization of pathologies. This system includes blocks: patient information input, medical image processing, to establish a conclusion, to classify the pathologies identified, a database and a report. In the proposed system, the initial step is to obtain tomographic or X-ray images, which are then transferred to the patient information and medical image processing units. Information about the patient as a result of the introduction enters the database along with tomographic or X-ray images. In the proposed system of recognition of tomographic and X-ray images for the search and localization of pathologies, there is an opportunity for the diagnostician to independently isolate a region that is suspicious from his point of view and subsequently process only this area, including using convolutional neural networks to highlight areas of pathologies, neoplasms, or choose specific algorithms for processing medical images. [ABSTRACT FROM AUTHOR] more...