Unfortunately, every day there is an increase in new diseases and their types in the world. To recognize and diagnose them in such a huge database is becoming increasingly difficult even for experienced doctors. Therefore, to solve this problem, deep learning methods have become a promising tool in the analysis of medical images. Their implementation and application in the medical industry will make it possible to provide fast and correct solutions. Therefore, due to the relevance of this area, this review discusses methods for analyzing medical images. A thorough analysis of various research articles in the field of deep learning methods and their application to the medical field was conducted. More than 800 research articles were examined, and after several stages of selection, 42 articles were presented in more detail. The results show that convolutional neural networks (CNNs) are the most widely used when it comes to medical image analysis. In addition, based on the findings of this article, it can be noted that the use of deep learning technologies is widespread. This is due to the annual increase in the amount of medical images and data. Manual methods of verification and analysis take more time than trained deep learning methods. Moreover, such tools provide better results and conclusions. The results of this review can be used by the professionals working in the sphere of medicine.