Tools for Automatically Finding and Visualizing Interest Areas in MRI Data to Support Decision Making by Medical Researchers

Abstract

This article gives a detailed description of the techniques developed by the authors for primary and deep processing of magnetic-resonance imaging that are aimed at detecting areas of ischemic lesion in the rat brain. The tools include the techniques for bringing MRI images of different samples to the normalized form (size, shape, and brightness). Another set of tools is associated with the detection of anomalies based on T2 and MDC images using artificial neural networks and specific metrics. It is assumed that the created algorithms and programs will be part of the developed research software system that is oriented to support decision making by medical researchers.