Segmentation of multiple sclerosis lesions using support vector machines

Ricardo J. Ferrari, Xingchang Wei, Yunyan Zhang, James N. Scott, Joseph Ross Mitchell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

In this paper we present preliminary results to automatically segment multiple sclerosis (MS) lesions in multispectral magnetic resonance datasets using support vector machines (SVM). A total of eighteen studies (each composed of T1-, T2-weighted and FLAIR images) acquired from a 3T GE Signa scanner was analyzed. A neuroradiologist used a computer-assisted technique to identify all MS lesions in each study. These results were used later in the training and testing stages of the SVM classifier. A preprocessing stage including anisotropic diffusion filtering, non-uniformity intensity correction, and intensity tissue normalization was applied to the images. The SVM kernel used in this study was the radial basis function (RBF). The kernel parameter (γ) and the penalty value for the errors (C) were determined by using a very loose stopping criterion for the SVM decomposition. Overall, a 5-fold cross-validation accuracy rate of 80% was achieved in the automatic classification of MS lesion voxels using the proposed SVM-RBF classifier.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM. Sonka, J.M. Fitzpatrick
Pages16-26
Number of pages11
Volume5032 I
DOIs
StatePublished - 2003
Externally publishedYes
EventMedical Imaging 2003: Image Processing - San Diego, CA, United States
Duration: Feb 17 2003Feb 20 2003

Other

OtherMedical Imaging 2003: Image Processing
CountryUnited States
CitySan Diego, CA
Period2/17/032/20/03

Fingerprint

lesions
Support vector machines
classifiers
Classifiers
Magnetic resonance
preprocessing
penalties
stopping
nonuniformity
scanners
magnetic resonance
education
Tissue
Decomposition
decomposition
Testing

Keywords

  • MRI
  • Multiple sclerosis
  • Segmentation of multiple sclerosis
  • Support vector machines

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Ferrari, R. J., Wei, X., Zhang, Y., Scott, J. N., & Mitchell, J. R. (2003). Segmentation of multiple sclerosis lesions using support vector machines. In M. Sonka, & J. M. Fitzpatrick (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5032 I, pp. 16-26) https://doi.org/10.1117/12.481377

Segmentation of multiple sclerosis lesions using support vector machines. / Ferrari, Ricardo J.; Wei, Xingchang; Zhang, Yunyan; Scott, James N.; Mitchell, Joseph Ross.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / M. Sonka; J.M. Fitzpatrick. Vol. 5032 I 2003. p. 16-26.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ferrari, RJ, Wei, X, Zhang, Y, Scott, JN & Mitchell, JR 2003, Segmentation of multiple sclerosis lesions using support vector machines. in M Sonka & JM Fitzpatrick (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5032 I, pp. 16-26, Medical Imaging 2003: Image Processing, San Diego, CA, United States, 2/17/03. https://doi.org/10.1117/12.481377
Ferrari RJ, Wei X, Zhang Y, Scott JN, Mitchell JR. Segmentation of multiple sclerosis lesions using support vector machines. In Sonka M, Fitzpatrick JM, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5032 I. 2003. p. 16-26 https://doi.org/10.1117/12.481377
Ferrari, Ricardo J. ; Wei, Xingchang ; Zhang, Yunyan ; Scott, James N. ; Mitchell, Joseph Ross. / Segmentation of multiple sclerosis lesions using support vector machines. Proceedings of SPIE - The International Society for Optical Engineering. editor / M. Sonka ; J.M. Fitzpatrick. Vol. 5032 I 2003. pp. 16-26
@inproceedings{e9e0fd0c11754efa9216981751298e3a,
title = "Segmentation of multiple sclerosis lesions using support vector machines",
abstract = "In this paper we present preliminary results to automatically segment multiple sclerosis (MS) lesions in multispectral magnetic resonance datasets using support vector machines (SVM). A total of eighteen studies (each composed of T1-, T2-weighted and FLAIR images) acquired from a 3T GE Signa scanner was analyzed. A neuroradiologist used a computer-assisted technique to identify all MS lesions in each study. These results were used later in the training and testing stages of the SVM classifier. A preprocessing stage including anisotropic diffusion filtering, non-uniformity intensity correction, and intensity tissue normalization was applied to the images. The SVM kernel used in this study was the radial basis function (RBF). The kernel parameter (γ) and the penalty value for the errors (C) were determined by using a very loose stopping criterion for the SVM decomposition. Overall, a 5-fold cross-validation accuracy rate of 80{\%} was achieved in the automatic classification of MS lesion voxels using the proposed SVM-RBF classifier.",
keywords = "MRI, Multiple sclerosis, Segmentation of multiple sclerosis, Support vector machines",
author = "Ferrari, {Ricardo J.} and Xingchang Wei and Yunyan Zhang and Scott, {James N.} and Mitchell, {Joseph Ross}",
year = "2003",
doi = "10.1117/12.481377",
language = "English (US)",
volume = "5032 I",
pages = "16--26",
editor = "M. Sonka and J.M. Fitzpatrick",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Segmentation of multiple sclerosis lesions using support vector machines

AU - Ferrari, Ricardo J.

AU - Wei, Xingchang

AU - Zhang, Yunyan

AU - Scott, James N.

AU - Mitchell, Joseph Ross

PY - 2003

Y1 - 2003

N2 - In this paper we present preliminary results to automatically segment multiple sclerosis (MS) lesions in multispectral magnetic resonance datasets using support vector machines (SVM). A total of eighteen studies (each composed of T1-, T2-weighted and FLAIR images) acquired from a 3T GE Signa scanner was analyzed. A neuroradiologist used a computer-assisted technique to identify all MS lesions in each study. These results were used later in the training and testing stages of the SVM classifier. A preprocessing stage including anisotropic diffusion filtering, non-uniformity intensity correction, and intensity tissue normalization was applied to the images. The SVM kernel used in this study was the radial basis function (RBF). The kernel parameter (γ) and the penalty value for the errors (C) were determined by using a very loose stopping criterion for the SVM decomposition. Overall, a 5-fold cross-validation accuracy rate of 80% was achieved in the automatic classification of MS lesion voxels using the proposed SVM-RBF classifier.

AB - In this paper we present preliminary results to automatically segment multiple sclerosis (MS) lesions in multispectral magnetic resonance datasets using support vector machines (SVM). A total of eighteen studies (each composed of T1-, T2-weighted and FLAIR images) acquired from a 3T GE Signa scanner was analyzed. A neuroradiologist used a computer-assisted technique to identify all MS lesions in each study. These results were used later in the training and testing stages of the SVM classifier. A preprocessing stage including anisotropic diffusion filtering, non-uniformity intensity correction, and intensity tissue normalization was applied to the images. The SVM kernel used in this study was the radial basis function (RBF). The kernel parameter (γ) and the penalty value for the errors (C) were determined by using a very loose stopping criterion for the SVM decomposition. Overall, a 5-fold cross-validation accuracy rate of 80% was achieved in the automatic classification of MS lesion voxels using the proposed SVM-RBF classifier.

KW - MRI

KW - Multiple sclerosis

KW - Segmentation of multiple sclerosis

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=0042376130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042376130&partnerID=8YFLogxK

U2 - 10.1117/12.481377

DO - 10.1117/12.481377

M3 - Conference contribution

AN - SCOPUS:0042376130

VL - 5032 I

SP - 16

EP - 26

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Sonka, M.

A2 - Fitzpatrick, J.M.

ER -