Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data

Peng Sun; Ye Wu; Geng Chen; Jun Wu; Dinggang Shen; Pew Thian Yap

doi:10.1007/978-3-030-05831-9_6

Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data

Peng Sun, Ye Wu, Geng Chen, Jun Wu, Dinggang Shen, Pew Thian Yap

Department of Brain and Cognitive Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

In this paper, we present a method based on sparse non-negative matrix factorization (NMF) for brain tissue segmentation using diffusion MRI (DMRI) data. Unlike existing NMF-based approaches, in our method NMF is applied to the spherical mean data, computed on a per-shell basis, instead of the original diffusion-weighted images. This is motivated by the fact that the spherical mean is independent of the fiber orientation distribution and is only dependent on tissue microstructure. Applying NMF to the spherical mean data will hence allow tissue signal separation based solely on the microstructural properties, unconfounded by factors such as fiber dispersion and crossing. We show results explaining why applying NMF directly on the diffusion-weighted images fails and why our method is able to yield the expected outcome, producing tissue segmentation with greater accuracy.

Original language	English
Title of host publication	Mathematics and Visualization
Editors	Elisenda Bonet-Carne, Francesco Grussu, Lipeng Ning, Farshid Sepehrband, Chantal M.W. Tax
Publisher	Springer Heidelberg
Pages	69-76
Number of pages	8
ISBN (Print)	9783030058302
DOIs	https://doi.org/10.1007/978-3-030-05831-9_6
Publication status	Published - 2019
Event	International Workshop on Computational Diffusion MRI, CDMRI 2018 held with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 - Granada, Spain Duration: 2018 Sept 20 → 2018 Sept 20

Publication series

Name	Mathematics and Visualization
ISSN (Print)	1612-3786
ISSN (Electronic)	2197-666X

Conference

Conference	International Workshop on Computational Diffusion MRI, CDMRI 2018 held with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018
Country/Territory	Spain
City	Granada
Period	18/9/20 → 18/9/20

Bibliographical note

Funding Information:
This work was supported in part by NIH grants (NS093842, EB022880, EB006733, EB009634, AG041721, MH100217, and AA012388) and NSFC grants (11671022 and 61502392).

Publisher Copyright:
© 2019, Springer Nature Switzerland AG.

Keywords

Diffusion MRI
Sparse NMF
Spherical mean
Tissue segmentation

ASJC Scopus subject areas

Modelling and Simulation
Geometry and Topology
Computer Graphics and Computer-Aided Design
Applied Mathematics

Access to Document

10.1007/978-3-030-05831-9_6

Cite this

Sun, P., Wu, Y., Chen, G., Wu, J., Shen, D., & Yap, P. T. (2019). Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data. In E. Bonet-Carne, F. Grussu, L. Ning, F. Sepehrband, & C. M. W. Tax (Eds.), Mathematics and Visualization (pp. 69-76). (Mathematics and Visualization). Springer Heidelberg. https://doi.org/10.1007/978-3-030-05831-9_6

Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data. / Sun, Peng; Wu, Ye; Chen, Geng et al.
Mathematics and Visualization. ed. / Elisenda Bonet-Carne; Francesco Grussu; Lipeng Ning; Farshid Sepehrband; Chantal M.W. Tax. Springer Heidelberg, 2019. p. 69-76 (Mathematics and Visualization).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sun, P, Wu, Y, Chen, G, Wu, J, Shen, D & Yap, PT 2019, Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data. in E Bonet-Carne, F Grussu, L Ning, F Sepehrband & CMW Tax (eds), Mathematics and Visualization. Mathematics and Visualization, Springer Heidelberg, pp. 69-76, International Workshop on Computational Diffusion MRI, CDMRI 2018 held with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018, Granada, Spain, 18/9/20. https://doi.org/10.1007/978-3-030-05831-9_6

@inproceedings{e44aca44f6664c24b84e056950eba869,

title = "Tissue Segmentation Using Sparse Non-negative Matrix Factorization of{\^A} Spherical Mean Diffusion MRI Data",

abstract = "In this paper, we present a method based on sparse non-negative matrix factorization (NMF) for brain tissue segmentation using diffusion MRI (DMRI) data. Unlike existing NMF-based approaches, in our method NMF is applied to the spherical mean data, computed on a per-shell basis, instead of the original diffusion-weighted images. This is motivated by the fact that the spherical mean is independent of the fiber orientation distribution and is only dependent on tissue microstructure. Applying NMF to the spherical mean data will hence allow tissue signal separation based solely on the microstructural properties, unconfounded by factors such as fiber dispersion and crossing. We show results explaining why applying NMF directly on the diffusion-weighted images fails and why our method is able to yield the expected outcome, producing tissue segmentation with greater accuracy.",

keywords = "Diffusion MRI, Sparse NMF, Spherical mean, Tissue segmentation",

author = "Peng Sun and Ye Wu and Geng Chen and Jun Wu and Dinggang Shen and Yap, {Pew Thian}",

note = "Funding Information: This work was supported in part by NIH grants (NS093842, EB022880, EB006733, EB009634, AG041721, MH100217, and AA012388) and NSFC grants (11671022 and 61502392). Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; International Workshop on Computational Diffusion MRI, CDMRI 2018 held with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 ; Conference date: 20-09-2018 Through 20-09-2018",

year = "2019",

doi = "10.1007/978-3-030-05831-9_6",

language = "English",

isbn = "9783030058302",

series = "Mathematics and Visualization",

publisher = "Springer Heidelberg",

pages = "69--76",

editor = "Elisenda Bonet-Carne and Francesco Grussu and Lipeng Ning and Farshid Sepehrband and Tax, {Chantal M.W.}",

booktitle = "Mathematics and Visualization",

}

TY - GEN

T1 - Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data

AU - Sun, Peng

AU - Wu, Ye

AU - Chen, Geng

AU - Wu, Jun

AU - Shen, Dinggang

AU - Yap, Pew Thian

N1 - Funding Information: This work was supported in part by NIH grants (NS093842, EB022880, EB006733, EB009634, AG041721, MH100217, and AA012388) and NSFC grants (11671022 and 61502392). Publisher Copyright: © 2019, Springer Nature Switzerland AG.

PY - 2019

Y1 - 2019

N2 - In this paper, we present a method based on sparse non-negative matrix factorization (NMF) for brain tissue segmentation using diffusion MRI (DMRI) data. Unlike existing NMF-based approaches, in our method NMF is applied to the spherical mean data, computed on a per-shell basis, instead of the original diffusion-weighted images. This is motivated by the fact that the spherical mean is independent of the fiber orientation distribution and is only dependent on tissue microstructure. Applying NMF to the spherical mean data will hence allow tissue signal separation based solely on the microstructural properties, unconfounded by factors such as fiber dispersion and crossing. We show results explaining why applying NMF directly on the diffusion-weighted images fails and why our method is able to yield the expected outcome, producing tissue segmentation with greater accuracy.

AB - In this paper, we present a method based on sparse non-negative matrix factorization (NMF) for brain tissue segmentation using diffusion MRI (DMRI) data. Unlike existing NMF-based approaches, in our method NMF is applied to the spherical mean data, computed on a per-shell basis, instead of the original diffusion-weighted images. This is motivated by the fact that the spherical mean is independent of the fiber orientation distribution and is only dependent on tissue microstructure. Applying NMF to the spherical mean data will hence allow tissue signal separation based solely on the microstructural properties, unconfounded by factors such as fiber dispersion and crossing. We show results explaining why applying NMF directly on the diffusion-weighted images fails and why our method is able to yield the expected outcome, producing tissue segmentation with greater accuracy.

KW - Diffusion MRI

KW - Sparse NMF

KW - Spherical mean

KW - Tissue segmentation

UR - http://www.scopus.com/inward/record.url?scp=85066880886&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-05831-9_6

DO - 10.1007/978-3-030-05831-9_6

M3 - Conference contribution

AN - SCOPUS:85066880886

SN - 9783030058302

T3 - Mathematics and Visualization

SP - 69

EP - 76

BT - Mathematics and Visualization

A2 - Bonet-Carne, Elisenda

A2 - Grussu, Francesco

A2 - Ning, Lipeng

A2 - Sepehrband, Farshid

A2 - Tax, Chantal M.W.

PB - Springer Heidelberg

T2 - International Workshop on Computational Diffusion MRI, CDMRI 2018 held with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018

Y2 - 20 September 2018 through 20 September 2018

ER -

Tissue Segmentation Using Sparse Non-negative Matrix Factorization ofÂ Spherical Mean Diffusion MRI Data

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this