Automatic segmentation and classification of multiple sclerosis in multichannel MRI.

Ayelet Akselrod-Ballin, Meirav Galun, John Moshe Gomori, Massimo Filippi, Paola Valsasina, Ronen Basri, Achi Brandt

Research output: Contribution to journalArticle

Abstract

We introduce a multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in automatically detecting multiple sclerosis (MS) lesions in 3-D multichannel magnetic resonance (MR) images. Our method uses segmentation to obtain a hierarchical decomposition of a multichannel, anisotropic MR scans. It then produces a rich set of features describing the segments in terms of intensity, shape, location, neighborhood relations, and anatomical context. These features are then fed into a decision forest classifier, trained with data labeled by experts, enabling the detection of lesions at all scales. Unlike common approaches that use voxel-by-voxel analysis, our system can utilize regional properties that are often important for characterizing abnormal brain structures. We provide experiments on two types of real MR images: a multichannel proton-density-, T2-, and T1-weighted dataset of 25 MS patients and a single-channel fluid attenuated inversion recovery (FLAIR) dataset of 16 MS patients. Comparing our results with lesion delineation by a human expert and with previously extensively validated results shows the promise of the approach.

Original languageEnglish
Pages (from-to)2461-2469
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume56
Issue number10
Publication statusPublished - Oct 2009

Fingerprint

Magnetic resonance
Magnetic resonance imaging
Multiple Sclerosis
Magnetic Resonance Spectroscopy
Brain
Imagery (Psychotherapy)
Protons
Classifiers
Decomposition
Recovery
Fluids
Experiments
Datasets

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Akselrod-Ballin, A., Galun, M., Gomori, J. M., Filippi, M., Valsasina, P., Basri, R., & Brandt, A. (2009). Automatic segmentation and classification of multiple sclerosis in multichannel MRI. IEEE Transactions on Biomedical Engineering, 56(10), 2461-2469.

Automatic segmentation and classification of multiple sclerosis in multichannel MRI. / Akselrod-Ballin, Ayelet; Galun, Meirav; Gomori, John Moshe; Filippi, Massimo; Valsasina, Paola; Basri, Ronen; Brandt, Achi.

In: IEEE Transactions on Biomedical Engineering, Vol. 56, No. 10, 10.2009, p. 2461-2469.

Research output: Contribution to journalArticle

Akselrod-Ballin, A, Galun, M, Gomori, JM, Filippi, M, Valsasina, P, Basri, R & Brandt, A 2009, 'Automatic segmentation and classification of multiple sclerosis in multichannel MRI.', IEEE Transactions on Biomedical Engineering, vol. 56, no. 10, pp. 2461-2469.
Akselrod-Ballin A, Galun M, Gomori JM, Filippi M, Valsasina P, Basri R et al. Automatic segmentation and classification of multiple sclerosis in multichannel MRI. IEEE Transactions on Biomedical Engineering. 2009 Oct;56(10):2461-2469.
Akselrod-Ballin, Ayelet ; Galun, Meirav ; Gomori, John Moshe ; Filippi, Massimo ; Valsasina, Paola ; Basri, Ronen ; Brandt, Achi. / Automatic segmentation and classification of multiple sclerosis in multichannel MRI. In: IEEE Transactions on Biomedical Engineering. 2009 ; Vol. 56, No. 10. pp. 2461-2469.
@article{9964eb32056449f68dbaa15870ec13b5,
title = "Automatic segmentation and classification of multiple sclerosis in multichannel MRI.",
abstract = "We introduce a multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in automatically detecting multiple sclerosis (MS) lesions in 3-D multichannel magnetic resonance (MR) images. Our method uses segmentation to obtain a hierarchical decomposition of a multichannel, anisotropic MR scans. It then produces a rich set of features describing the segments in terms of intensity, shape, location, neighborhood relations, and anatomical context. These features are then fed into a decision forest classifier, trained with data labeled by experts, enabling the detection of lesions at all scales. Unlike common approaches that use voxel-by-voxel analysis, our system can utilize regional properties that are often important for characterizing abnormal brain structures. We provide experiments on two types of real MR images: a multichannel proton-density-, T2-, and T1-weighted dataset of 25 MS patients and a single-channel fluid attenuated inversion recovery (FLAIR) dataset of 16 MS patients. Comparing our results with lesion delineation by a human expert and with previously extensively validated results shows the promise of the approach.",
author = "Ayelet Akselrod-Ballin and Meirav Galun and Gomori, {John Moshe} and Massimo Filippi and Paola Valsasina and Ronen Basri and Achi Brandt",
year = "2009",
month = "10",
language = "English",
volume = "56",
pages = "2461--2469",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - Automatic segmentation and classification of multiple sclerosis in multichannel MRI.

AU - Akselrod-Ballin, Ayelet

AU - Galun, Meirav

AU - Gomori, John Moshe

AU - Filippi, Massimo

AU - Valsasina, Paola

AU - Basri, Ronen

AU - Brandt, Achi

PY - 2009/10

Y1 - 2009/10

N2 - We introduce a multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in automatically detecting multiple sclerosis (MS) lesions in 3-D multichannel magnetic resonance (MR) images. Our method uses segmentation to obtain a hierarchical decomposition of a multichannel, anisotropic MR scans. It then produces a rich set of features describing the segments in terms of intensity, shape, location, neighborhood relations, and anatomical context. These features are then fed into a decision forest classifier, trained with data labeled by experts, enabling the detection of lesions at all scales. Unlike common approaches that use voxel-by-voxel analysis, our system can utilize regional properties that are often important for characterizing abnormal brain structures. We provide experiments on two types of real MR images: a multichannel proton-density-, T2-, and T1-weighted dataset of 25 MS patients and a single-channel fluid attenuated inversion recovery (FLAIR) dataset of 16 MS patients. Comparing our results with lesion delineation by a human expert and with previously extensively validated results shows the promise of the approach.

AB - We introduce a multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in automatically detecting multiple sclerosis (MS) lesions in 3-D multichannel magnetic resonance (MR) images. Our method uses segmentation to obtain a hierarchical decomposition of a multichannel, anisotropic MR scans. It then produces a rich set of features describing the segments in terms of intensity, shape, location, neighborhood relations, and anatomical context. These features are then fed into a decision forest classifier, trained with data labeled by experts, enabling the detection of lesions at all scales. Unlike common approaches that use voxel-by-voxel analysis, our system can utilize regional properties that are often important for characterizing abnormal brain structures. We provide experiments on two types of real MR images: a multichannel proton-density-, T2-, and T1-weighted dataset of 25 MS patients and a single-channel fluid attenuated inversion recovery (FLAIR) dataset of 16 MS patients. Comparing our results with lesion delineation by a human expert and with previously extensively validated results shows the promise of the approach.

UR - http://www.scopus.com/inward/record.url?scp=74049148759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74049148759&partnerID=8YFLogxK

M3 - Article

C2 - 19758850

AN - SCOPUS:74049148759

VL - 56

SP - 2461

EP - 2469

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

ER -