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

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.

Deep Learning Based Segmentation of Brain Tissue from Diffusion MRI

“…Our proposed method performed tissue segmentation prediction directly from the dMRI data and thus could avoid obvious segmentation errors when transferring the anatomical T2w-based "ground truth" segmentation to the dMRI space. In the literature, anatomical-MRI-based segmentation, e.g., the one obtained by SPM, is usually used as the "ground truth" data (Ciritsis et al, 2018;Schnell et al, 2009;Cheng et al, 2020), since the segmentation appears in good agreement with the known anatomy. However, transferring T1w-or T2wbased segmentation into the dMRI space is challenging due to the image distortions in dMRI data, which affected inter-modality registration significantly (Albi et al, 2018;Wu et al, 2008;Jones and Cercignani, 2010).…”

“…The labels were projected into the co-registered dMRI data using nearest neighbor interpolation. We note that SPM is often the method of choice in generating high quality reference brain segmentation to compare with dMRI-based tissue segmentation (Schnell et al, 2009;Ciritsis et al, 2018;Cheng et al, 2020), although other segmentation tools, e.g., FMRIB's Automated Segmentation Tool (FSL FAST) (Jenkinson et al, 2012) could also be used instead.…”

“…Most dMRI-based brain tissue segmentation methods use features derived from the diffusion tensor imaging (DTI) model, such as mean diffusivity (MD) and fractional anisotropy (FA) (Liu et al, 2007;Schnell et al, 2009;Wen et al, 2013;Kumazawa et al, 2013;Yap et al, 2015;Ciritsis et al, 2018;Zhang et al, 2015;Nie et al, 2018). These DTI-based studies have achieved limited accuracy partly because DTI is known to be non-specific in characterization of water diffusion in the complex intracellular and extracellular in vivo environment (O'Donnell and Pasternak, 2015).…”

Segmentation of the brain using direction-averaged signal of DWI images

“…Recently, Yap P et al applied l0 sparse-group representation classification on the raw DWI data and achieved a Dice score of ~0.8 for GM and ~0.86 for WM on five subjects when using T1w segmentation as the ground truth [10]. Another method using machine learning achieved an average Dice score of 0.79 by taking the diffusion weighted signal as well as the MD and FA values as features [11].…”

A points of interest matching method using a multivariate weighting function with gradient descent optimization

“…Related studies show that as algorithms can be improved automatically through experience, machine learning has higher accuracy and scalability than more common methods (Zhang & El‐Gohary, 2020). Moreover, machine learning has been widely used in various classification problems such as image classification and text classification (Ciritsis, Boss, & Rossi, 2018; Zablith & Osman, 2019), which makes it suitable for POI matching.…”