MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU

Stamos Katsigiannis, Eleni Zacharia, Dimitris Maroulis

Research output: Contribution to journalArticle

Abstract

cDNA microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images which often suffer from noise, artifacts, and uneven background. In this work, the MIGS-GPU (Microarray Image Gridding and Segmentation on GPU) software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the graphics processing unit (GPU) by means of the CUDA architecture in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a userfriendly interface that requires minimum input in order to run.

Original languageEnglish
Pages (from-to)867-874
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume21
Issue number3
DOIs
Publication statusPublished - 3 Mar 2016
Externally publishedYes

Fingerprint

Microarrays
Oligonucleotide Array Sequence Analysis
Microarray Analysis
Artifacts
Noise
Software
Genes
Graphics processing unit
Program processors

Keywords

  • Journal Article

Cite this

@article{640638f0a0104e84802ac1174b3ea47b,
title = "MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU",
abstract = "cDNA microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images which often suffer from noise, artifacts, and uneven background. In this work, the MIGS-GPU (Microarray Image Gridding and Segmentation on GPU) software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the graphics processing unit (GPU) by means of the CUDA architecture in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a userfriendly interface that requires minimum input in order to run.",
keywords = "Journal Article",
author = "Stamos Katsigiannis and Eleni Zacharia and Dimitris Maroulis",
year = "2016",
month = "3",
day = "3",
doi = "10.1109/JBHI.2016.2537922",
language = "English",
volume = "21",
pages = "867--874",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "IEEE",
number = "3",

}

MIGS-GPU : Microarray Image Gridding and Segmentation on the GPU. / Katsigiannis, Stamos; Zacharia, Eleni; Maroulis, Dimitris.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 21, No. 3, 03.03.2016, p. 867-874.

Research output: Contribution to journalArticle

TY - JOUR

T1 - MIGS-GPU

T2 - Microarray Image Gridding and Segmentation on the GPU

AU - Katsigiannis, Stamos

AU - Zacharia, Eleni

AU - Maroulis, Dimitris

PY - 2016/3/3

Y1 - 2016/3/3

N2 - cDNA microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images which often suffer from noise, artifacts, and uneven background. In this work, the MIGS-GPU (Microarray Image Gridding and Segmentation on GPU) software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the graphics processing unit (GPU) by means of the CUDA architecture in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a userfriendly interface that requires minimum input in order to run.

AB - cDNA microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images which often suffer from noise, artifacts, and uneven background. In this work, the MIGS-GPU (Microarray Image Gridding and Segmentation on GPU) software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the graphics processing unit (GPU) by means of the CUDA architecture in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a userfriendly interface that requires minimum input in order to run.

KW - Journal Article

U2 - 10.1109/JBHI.2016.2537922

DO - 10.1109/JBHI.2016.2537922

M3 - Article

VL - 21

SP - 867

EP - 874

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

ER -