Methods of Intellectual Analysis in Medical Diagnostic Tasks Using Smart Feature Selection

Abstract

The paper deals with a computer technique for high-performance processing, analysis and interpretation of medical and diagnostic images. We propose a new approach to the analysis of different classes of images based on evaluation of aggregate geometric and texture parameters of allocated regions of interest which are supposed to be a basic feature set. The developed efficient feature-space generation technique is based on Big Data mining of unstructured information by applying the discriminative analysis methods. The technique makes it possible to extract regions of interest on fundus images containing four classes of objects: exudates, intact areas, thick vessels, and thin vessels. The use of Big Data technology made it possible, due to involving large amounts of data, to improve the training sample and reduce classification errors that ensured an increase of diagnosis accuracy up to 95%. The proposed technique has been applied to the coagulate location problem, that is a crucial problem of diabetic retinopathy treatment. The experiment results on real eye fundus images proved a considerable increase of treatment effectiveness.