Biomedical Data Analysis Based on Parallel Programming Technology Application for Computation Features' Effectiveness

This paper proposes a technology for large biomedical data analyzing based on CUDA computation. The technology was used to analyze a large set of fundus images used for diabetic retinopathy automatic diagnostics. A highperformance algorithm has been developed to calculate effective textural characteristics for medical image analysis. During the automatic image diagnostics, the following classes were distinguished: thin vessels, thick vessels, exudates and healthy areas. The mentioned algorithm's efficiency study was conducted with 500×500-1000×1000 pixels images using a 12×12 dimension window. The relationship between the developed algorithm's acceleration and data sizes was demonstrated. The study showed that the algorithm effectiveness can be depends of certain characteristics of the image, as its clarity, the shape of exudate zone, the variability of blood vessels, and the optic disc's location.