Header

UZH-Logo

Maintenance Infos

Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning


Ciritsis, Alexander; Boss, Andreas; Rossi, Cristina (2018). Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning. NMR in Biomedicine, 31(7):e3931.

Abstract

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3 T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79 ± 0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200 s/mm and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC = 0.79 ± 0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information.

Abstract

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3 T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79 ± 0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200 s/mm and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC = 0.79 ± 0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information.

Statistics

Citations

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Diagnostic and Interventional Radiology
Dewey Decimal Classification:610 Medicine & health
Uncontrolled Keywords:Spectroscopy, Molecular Medicine, Radiology Nuclear Medicine and imaging
Language:English
Date:26 April 2018
Deposited On:22 May 2018 15:06
Last Modified:19 Aug 2018 15:45
Publisher:Wiley-Blackwell Publishing, Inc.
ISSN:0952-3480
OA Status:Closed
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1002/nbm.3931
PubMed ID:29697165

Download

Full text not available from this repository.
View at publisher

Get full-text in a library