Analysis of dynamic texture and spatial spectral descriptors of dynamic contrast-enhanced brain magnetic resonance images for studying small vessel disease

Abstract

Cerebral small vessel disease (SVD) comprises various pathological processes affecting small brain vessels and damaging white and grey matter. In this paper, we propose a framework comprising region of interest sampling, dynamic spectral and texture description, functional principal component analysis, and statistical analysis to study exogenous contrast agent distribution over time in various brain regions in patients with recent mild stroke and SVD features.We compared our results against current semi-quantitative surrogates of dysfunction such as signal enhancement area and slope. Biological sex, stroke lesion type and overall burden of white matter hyperintensities (WMH) were significant predictors of intensity, spectral, and texture features extracted from the ventricular region (p-value < 0.05), explaining between a fifth and a fourth of the data variance (0.20 ≤Adj.R² ≤ 0.25). We observed that spectral feature reflected more the dysfunction compared to other descriptors since the overall WMH burden explained consistently the power spectra variability in blood vessels, cerebrospinal fluid, deep grey matter and white matter. Our preliminary results show the potential of the framework for the analysis of dynamic contrast-enhanced brain magnetic resonance imaging acquisitions in SVD since significant variation in our metrics was related to the burden of SVD features. Therefore, our proposal may increase sensitivity to detect subtle features of small vessel dysfunction. A public version of the code will be released on our research website.

Keywords: Cerebral small vessel disease; Dynamic brain magnetic resonance image; Dynamic descriptors; Principal component analysis.

Fig. 1

Scheme of our processing pipeline. The inputs are the DCE-MRI sequences (1). Initially, we process each case by sampling all regions of interest using an anatomically-relevant template (2), describing local signal variations in regions of interest using descriptors (3). Subsequently, we study the dynamic descriptors using functional principal component analysis (4) and statistical analysis (5). ROI: region of interest. FPCA: functional principal component analysis. T₁,…,T_TP: each time point of the DCE-MRIs. Subject₁,…,Subject_P: each patient in the cohort. ROI₁,…,ROI_R: each region of interest.

Fig. 2

Example of selected regions of interest on four slices. From left to right, low, low-middle, middle-high, and high slices. Colour code is red, green, light blue, dark blue, and yellow for arteries and sagittal sinus, CSF, WM, GMD and GMC, respectively. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)