An integrative classification model for multiple sclerosis lesion detection in multimodal MRI

Fengqing (Zoe) Zhang*, Jiping Wang, Wenxin Jiang

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

We study a classification problem of multiple sclerosis (MS) lesions in three dimensional brain magnetic resonance (MR) images. Segmentation of MS lesions is essential for MS diagnosis, assessment of disease progression and evaluation of treatment efficacy. Accurate identification of MS lesions in MR images is challenging due to variability in lesion location, size and shape in addition to anatomical variability between subjects. We propose a supervised classification algorithm for segmenting MS lesions, which integrates the intensity information from multiple MRI modalities, the texture information, and the spatial information in a Bayesian framework. A multinomial logistic regression is employed to learn the posterior probability distributions from the intensity information, combined from three MRI modalities. Texture features are selected by the Elastic Net model. The spatial information is then incorporated using a Markov random field prior. Finally, a maximum a posteriori segmentation is obtained by the graph cuts algorithm. We illustrate the effectiveness of our proposed model for lesion segmentation using both the synthetic BrainWeb data and the clinical neuroimaging data.

Original languageEnglish (US)
Pages (from-to)193-202
Number of pages10
JournalStatistics and its Interface
Volume12
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Multiple Sclerosis
Magnetic resonance
Magnetic resonance imaging
Textures
Neuroimaging
Magnetic Resonance Image
Segmentation
Probability distributions
Spatial Information
Logistics
Brain
Modality
Elastic Net
Graph Cuts
Model
Supervised Classification
Texture Feature
Maximum a Posteriori
Posterior Probability
Classification Algorithm

Keywords

  • Multimodal MRI
  • Multiple sclerosis
  • Segmentation
  • Supervised classification algorithm

ASJC Scopus subject areas

  • Statistics and Probability
  • Applied Mathematics

Cite this

@article{02ae550fcde7482e9bb9c6a1bca3ce29,
title = "An integrative classification model for multiple sclerosis lesion detection in multimodal MRI",
abstract = "We study a classification problem of multiple sclerosis (MS) lesions in three dimensional brain magnetic resonance (MR) images. Segmentation of MS lesions is essential for MS diagnosis, assessment of disease progression and evaluation of treatment efficacy. Accurate identification of MS lesions in MR images is challenging due to variability in lesion location, size and shape in addition to anatomical variability between subjects. We propose a supervised classification algorithm for segmenting MS lesions, which integrates the intensity information from multiple MRI modalities, the texture information, and the spatial information in a Bayesian framework. A multinomial logistic regression is employed to learn the posterior probability distributions from the intensity information, combined from three MRI modalities. Texture features are selected by the Elastic Net model. The spatial information is then incorporated using a Markov random field prior. Finally, a maximum a posteriori segmentation is obtained by the graph cuts algorithm. We illustrate the effectiveness of our proposed model for lesion segmentation using both the synthetic BrainWeb data and the clinical neuroimaging data.",
keywords = "Multimodal MRI, Multiple sclerosis, Segmentation, Supervised classification algorithm",
author = "{(Zoe) Zhang}, Fengqing and Jiping Wang and Wenxin Jiang",
year = "2019",
month = "1",
day = "1",
doi = "10.4310/SII.2019.v12.n2.a1",
language = "English (US)",
volume = "12",
pages = "193--202",
journal = "Statistics and its Interface",
issn = "1938-7989",
publisher = "International Press of Boston, Inc.",
number = "2",

}

An integrative classification model for multiple sclerosis lesion detection in multimodal MRI. / (Zoe) Zhang, Fengqing; Wang, Jiping; Jiang, Wenxin.

In: Statistics and its Interface, Vol. 12, No. 2, 01.01.2019, p. 193-202.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An integrative classification model for multiple sclerosis lesion detection in multimodal MRI

AU - (Zoe) Zhang, Fengqing

AU - Wang, Jiping

AU - Jiang, Wenxin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We study a classification problem of multiple sclerosis (MS) lesions in three dimensional brain magnetic resonance (MR) images. Segmentation of MS lesions is essential for MS diagnosis, assessment of disease progression and evaluation of treatment efficacy. Accurate identification of MS lesions in MR images is challenging due to variability in lesion location, size and shape in addition to anatomical variability between subjects. We propose a supervised classification algorithm for segmenting MS lesions, which integrates the intensity information from multiple MRI modalities, the texture information, and the spatial information in a Bayesian framework. A multinomial logistic regression is employed to learn the posterior probability distributions from the intensity information, combined from three MRI modalities. Texture features are selected by the Elastic Net model. The spatial information is then incorporated using a Markov random field prior. Finally, a maximum a posteriori segmentation is obtained by the graph cuts algorithm. We illustrate the effectiveness of our proposed model for lesion segmentation using both the synthetic BrainWeb data and the clinical neuroimaging data.

AB - We study a classification problem of multiple sclerosis (MS) lesions in three dimensional brain magnetic resonance (MR) images. Segmentation of MS lesions is essential for MS diagnosis, assessment of disease progression and evaluation of treatment efficacy. Accurate identification of MS lesions in MR images is challenging due to variability in lesion location, size and shape in addition to anatomical variability between subjects. We propose a supervised classification algorithm for segmenting MS lesions, which integrates the intensity information from multiple MRI modalities, the texture information, and the spatial information in a Bayesian framework. A multinomial logistic regression is employed to learn the posterior probability distributions from the intensity information, combined from three MRI modalities. Texture features are selected by the Elastic Net model. The spatial information is then incorporated using a Markov random field prior. Finally, a maximum a posteriori segmentation is obtained by the graph cuts algorithm. We illustrate the effectiveness of our proposed model for lesion segmentation using both the synthetic BrainWeb data and the clinical neuroimaging data.

KW - Multimodal MRI

KW - Multiple sclerosis

KW - Segmentation

KW - Supervised classification algorithm

UR - http://www.scopus.com/inward/record.url?scp=85063731991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063731991&partnerID=8YFLogxK

U2 - 10.4310/SII.2019.v12.n2.a1

DO - 10.4310/SII.2019.v12.n2.a1

M3 - Article

VL - 12

SP - 193

EP - 202

JO - Statistics and its Interface

JF - Statistics and its Interface

SN - 1938-7989

IS - 2

ER -