View in EDS

CUDA parallel programming technology application for analysis of big biomedical data based on computation of effectiveness features

Saved in:
Bibliographic Details
Title: CUDA parallel programming technology application for analysis of big biomedical data based on computation of effectiveness features
Authors: Ilyasova, N Yu, Shikhevich, V A, Shirokanev, A S
Source: Journal of Physics: Conference Series ; volume 1368, issue 5, page 052006 ; ISSN 1742-6588 1742-6596
Publisher Information: IOP Publishing
Publication Year: 2019
Description: This paper proposes the technology for large biomedical data analysis based on CUDA computation. The technology was used to analyze a large set of fundus images used for diabetic retinopathy automatic diagnostics. A high-performance algorithm that calculates effective textural characteristics for medical image analysis has been developed. During the automatic image diagnostics, the following classes were distinguished: thin vessels, thick vessels, exudates and a healthy area. The study of the mentioned algorithm efficiency was conducted with 500x500-1000x1000 pixels images using a square 12x12 dimension window. The acceleration relationship between the developed algorithm and various data sizes was demonstrated. The study showed that the algorithm effectiveness can be affected by certain characteristics of the image, e.g. its clarity, shape of exudate zone, variability of blood vessels, and optic disc location.
Document Type: article in journal/newspaper
Language: unknown
DOI: 10.1088/1742-6596/1368/5/052006
DOI: 10.1088/1742-6596/1368/5/052006/pdf
Availability: https://doi.org/10.1088/1742-6596/1368/5/052006
https://iopscience.iop.org/article/10.1088/1742-6596/1368/5/052006/pdf
https://iopscience.iop.org/article/10.1088/1742-6596/1368/5/052006
Rights: http://creativecommons.org/licenses/by/3.0/ ; https://iopscience.iop.org/info/page/text-and-data-mining
Accession Number: edsbas.5B54BB3B
Database: BASE
Description
Abstract:This paper proposes the technology for large biomedical data analysis based on CUDA computation. The technology was used to analyze a large set of fundus images used for diabetic retinopathy automatic diagnostics. A high-performance algorithm that calculates effective textural characteristics for medical image analysis has been developed. During the automatic image diagnostics, the following classes were distinguished: thin vessels, thick vessels, exudates and a healthy area. The study of the mentioned algorithm efficiency was conducted with 500x500-1000x1000 pixels images using a square 12x12 dimension window. The acceleration relationship between the developed algorithm and various data sizes was demonstrated. The study showed that the algorithm effectiveness can be affected by certain characteristics of the image, e.g. its clarity, shape of exudate zone, variability of blood vessels, and optic disc location.
DOI:10.1088/1742-6596/1368/5/052006