Artificial intelligence technology in MR neuroimaging. А radiologist’s perspective

Abstract

Artificial Intelligence (AI) has been the subject of particular interest in the field of radiology in recent years. Experts believe that the development and implementation of AI technologies will improve diagnostic accuracy, speed up the acquisition of objective information, reduce its variability, and optimize the workflow of diagnostic departments of medical institutions. Over the years, AI has evolved from simple rule-based systems to sophisticated deep-learning algorithms capable of analysing medical images with high accuracy.Despite some progress, the use of AI in medical imaging is still limited. There are many challenges that need to be overcome before it can be widely adopted in clinical practice. For example, training AI algorithms require large amounts of high quality annotated data, and such data is not yet available for the bulk of pathology and any of the imaging techniques. This article looks at the possibilities of AI and some of the current challenges associated with the application of AI in neuroimaging.