Automated pixel‐wise brain tissue segmentation of diffusion‐weighted images via machine learning. (26th April 2018)

• Record Type: Journal Article
• Authors: Ciritsis, Alexander; Boss, Andreas; Rossi, Cristina
• Is Part Of: NMR in biomedicine. Volume 31:Number 7(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-04-26
• Subjects: DWI brain MRI -- IVIM -- machine learning -- segmentation; Nuclear magnetic resonance -- Periodicals; Magnetic Resonance Spectroscopy -- Periodicals; 574
• DOI: 10.1002/nbm.3931
• Languages: English
• ISSNs: 0952-3480

Abstract

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 2 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 1 ‐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 2 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 : A, A machine learning algorithm for automatic brain tissue segmentation from DW‐MRI datasets was implemented and compared with standard pixel‐wise classification performed on T 1 ‐weighted datasets. B, The algorithm resulted in an accuracy of over 82%. C, Accounting for the five most important features led to a comparable accuracy of 81%. Machine learning applied to optimally sampled DWI data allows for accurate brain tissue segmentation based on both morphological and functional tissue information.