Designing a pattern recognition system on GPU for discriminating between patients with micro-ischaemic and multiple sclerosis lesions,using MRI images

Abstract

The aim of this study was to employ state-of-art graphics processing unit (GPU) technology and CUDA parallel programming to design and implement a stand-alone pattern recognition (PR) system to discriminate between patients with micro-ischaemic (mIS) and multiple sclerosis (MS) lesions. The dataset comprised MRI image series of 32 patients with mIS and 19 with MS lesions. The probabilistic neural network classifier and 40 textural features, calculated from lesions in the magnetic resonance imaging (MRI) images, were used to design the PR system. The highest classification accuracy was 90.2%, employing six textural features. It took about 135 minutes to design the PR system on a desktop CPU (Intel Core 2 Quad Q9550), using sequential programming, against 250 seconds on the Nvidia 8800GT GPU card, using parallel programming. The proposed PR system may be redesigned on site, when new verified data are incorporated in its depository, and it may serve as a second opinion tool in a clinical environment.

Keywords

graphics processor unit parallel processing pattern recognition magnetic resonance imaging multiple sclerosis ischaemic lesions

Get full access to this article

View all access options for this article.

References

Ahmed

Rao

(1975) Orthogonal Transforms for Digital Signal Processing. New York: Springer-Verlag.

Ambroise

McLachlan

(2002) Selection bias in gene extraction on the basis of microarray gene-expression data. Proceedings of the National Academy of Sciences of the U S A 99: 6562–6566.

Bot

Barkhof

Lycklama a Nijeholt

. (2002) Differentiation of multiple sclerosis from other inflammatory disorders and cerebrovascular disease: value of spinal MR imaging. Radiology 223: 46–56.

Charil

Yousry

Rovaris

. (2006) MRI and the diagnosis of multiple sclerosis: expanding the concept of “no better explanation”. The Lancet Neurology 5: 841–852.

Galloway

(1975) Texture analysis using gray-level run lengths. Computer Graphics and Image Processing 4: 172–179.

Haralick

Shanmugam

Dinstein

(1973) Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics 3: 610–621.

Hoque

Ledbetter

Gonzalez-Toledo

. (2007) The role of quantitative neuroimaging indices in the differentiation of ischemia from demyelination: an analytical study with case presentation. International Review of Neurobiology 79: 491–519.

Kecman

(2001) Learning and soft computing: support vector machines, neural networks, and fuzzy logic models. Cambridge, MA: The MIT Press.

Kirk

Hwu

W-mW

(2010) Programming Massively Parallel Processors A Hands-on Approach. Amsterdam: Morgan Kaufmann.

10.

Lou

Jiang

. (2009) Lower fractional anisotropy at the anterior body of the normal-appearing corpus callosum in multiple sclerosis versus symptomatic carotid occlusion. Neuroradiology 51: 557–561.

11.

Mathias

Tofts

Losseff

(1999) Texture analysis of spinal cord pathology in multiple sclerosis. Magnetic Resonance in Medicine 42: 929–935.

12.

Montalban

Tintore

Swanton

. (2010) MRI criteria for MS in patients with clinically isolated syndromes. Neurology 74: 427–434.

13.

Sidiropoulos

Glotsos

Kostopoulos

. (2012) Real time decision support system for diagnosis of rare cancers, trained in parallel, on a graphics processing unit. Computers in Biology and Medicine 42: 376–386.

14.

Specht

(1990) Probabilistic neural networks. Neural Networks 3: 109–118.

15.

Theocharakis

Glotsos

Kalatzis

. (2009) Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images. Magnetic Resonance Imaging 27: 417–422.

16.

Theodoridis

Koutroumbas

(2003) Pattern Recognition. San Diego, CA: Elsevier.

17.

Trojano

(2011) Multiple sclerosis: the evolving diagnostic criteria for multiple sclerosis. Nature Reviews Neurology 7: 251–252.

18.

Mauss

Zollner

. (1999) Distinct patterns of active and non-active plaques using texture analysis on brain NMR images in multiple sclerosis patients: preliminary results. Magnetic Resonance Imaging 17: 1261–1267.

19.

Zhang

(2012) MRI texture analysis in multiple sclerosis. International Journal of Biomedical Imaging, in press.