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 |
---|---|
Pages (from-to) | 69-76 |
Number of pages | 8 |
Journal | Mathematics and Visualization |
Issue number | 226249 |
DOIs | |
Publication status | Published - 2019 Jan 1 |
Externally published | Yes |
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 Sep 20 → 2018 Sep 20 |
Fingerprint
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
Cite this
Tissue Segmentation Using Sparse Non-negative Matrix Factorization of Spherical Mean Diffusion MRI Data. / Sun, Peng; Wu, Ye; Chen, Geng; Wu, Jun; Shen, Dinggang; Yap, Pew Thian.
In: Mathematics and Visualization, No. 226249, 01.01.2019, p. 69-76.Research output: Contribution to journal › Conference article
}
TY - JOUR
T1 - Tissue Segmentation Using Sparse Non-negative Matrix Factorization of Spherical Mean Diffusion MRI Data
AU - Sun, Peng
AU - Wu, Ye
AU - Chen, Geng
AU - Wu, Jun
AU - Shen, Dinggang
AU - Yap, Pew Thian
PY - 2019/1/1
Y1 - 2019/1/1
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
UR - http://www.scopus.com/inward/citedby.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 article
AN - SCOPUS:85066880886
SP - 69
EP - 76
JO - Mathematics and Visualization
JF - Mathematics and Visualization
SN - 1612-3786
IS - 226249
ER -