Share Email Print
cover

Proceedings Paper

Performance evaluation for volumetric segmentation of multiple sclerosis lesions using MATLAB and computing engine in the graphical processing unit (GPU)
Author(s): Anh H. Le; Young W. Park; Kevin Ma; Colin Jacobs; Brent J. Liu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Multiple Sclerosis (MS) is a progressive neurological disease affecting myelin pathways in the brain. Multiple lesions in the white matter can cause paralysis and severe motor disabilities of the affected patient. To solve the issue of inconsistency and user-dependency in manual lesion measurement of MRI, we have proposed a 3-D automated lesion quantification algorithm to enable objective and efficient lesion volume tracking. The computer-aided detection (CAD) of MS, written in MATLAB, utilizes K-Nearest Neighbors (KNN) method to compute the probability of lesions on a per-voxel basis. Despite the highly optimized algorithm of imaging processing that is used in CAD development, MS CAD integration and evaluation in clinical workflow is technically challenging due to the requirement of high computation rates and memory bandwidth in the recursive nature of the algorithm. In this paper, we present the development and evaluation of using a computing engine in the graphical processing unit (GPU) with MATLAB for segmentation of MS lesions. The paper investigates the utilization of a high-end GPU for parallel computing of KNN in the MATLAB environment to improve algorithm performance. The integration is accomplished using NVIDIA's CUDA developmental toolkit for MATLAB. The results of this study will validate the practicality and effectiveness of the prototype MS CAD in a clinical setting. The GPU method may allow MS CAD to rapidly integrate in an electronic patient record or any disease-centric health care system.

Paper Details

Date Published: 12 March 2010
PDF: 6 pages
Proc. SPIE 7628, Medical Imaging 2010: Advanced PACS-based Imaging Informatics and Therapeutic Applications, 76280W (12 March 2010); doi: 10.1117/12.844811
Show Author Affiliations
Anh H. Le, Image Processing and Informatics Lab., The Univ. of Southern California (United States)
Young W. Park, Image Processing and Informatics Lab., The Univ. of Southern California (United States)
Kevin Ma, Image Processing and Informatics Lab., The Univ. of Southern California (United States)
Colin Jacobs, Image Processing and Informatics Lab., The Univ. of Southern California (United States)
Brent J. Liu, Image Processing and Informatics Lab., The Univ. of Southern California (United States)


Published in SPIE Proceedings Vol. 7628:
Medical Imaging 2010: Advanced PACS-based Imaging Informatics and Therapeutic Applications
Brent J. Liu; William W. Boonn, Editor(s)

© SPIE. Terms of Use
Back to Top