Abstract
Today, computed tomography and magnetic resonance imaging of the brain occupies the main place in the diagnosis of acute stroke. To improve the reliability of CT and MRI image analysis, it is advisable to develop an automated recognition system using neural networks of machine and deep learning. This article discusses the use of machine learning methods on computer and magnetic resonance imaging (CT and MRI) for the diagnosis of acute cerebral circulation disorders.Our goal consists of three parts: (1) to provide a brief introduction to machine learning with pointers to the main links; (2) to show how machine learning has been applied to the entire MRI and CT processing chain, from image acquisition to image acquisition, from segmentation to disease prediction; (3) provide a starting point for people interested in experimenting and possibly contributing to the field of deep learning medical imaging, pointing to good educational resources, modern open source code, and interesting data sources and problem-related medical images.