Abstract
Recent diffusion MRI studies of stroke in humans and animals have shown that the quantitative parameters characterising the degree of non-Gaussianity of the diffusion process are much more sensitive to ischemic changes than the apparent diffusion coefficient (ADC) considered so far as the “gold standard”. The observed changes exceeded that of the ADC by a remarkable factor of 2 to 3. These studies were based on the novel non-Gaussian methods, such as diffusion kurtosis imaging (DKI) and log-normal distribution function imaging (LNDFI). As shown in our previous work investigating the animal stroke model, a combined analysis using two methods, DKI and LNDFI provides valuable complimentary information. In the present work, we report the application of three non-Gaussian diffusion models to quantify the deviations from the Gaussian behaviour in stroke induced by transient middle cerebral artery occlusion in rat brains: the gamma-distribution function (GDF), the stretched exponential model (SEM), and the biexponential model. The main goal was to compare the sensitivity of various non-Gaussian metrics to ischemic changes and to investigate if a combined application of several models will provide added value in the assessment of stroke. We have shown that two models, GDF and SEM, exhibit a better performance than the conventional method and allow for a significantly enhanced visualization of lesions. Furthermore, we showed that valuable information regarding spatial properties of stroke lesions can be obtained. In particular, we observed a stratified cortex structure in the lesions that were well visible in the maps of the GDF and SEM metrics, but poorly distinguishable in the ADC-maps. Our results provided evidence that cortical layers tend to be differently affected by ischemic processes.
Highlights
Diffusion magnetic resonance imaging (MRI) is known as an important tool in early diagnostics and assessment of stroke [1,2]
Previous results have demonstrated that the peak diffusivity, DLD, and the scale parameter, sLD, of the log-normal distribution function imaging (LNDFI) model exhibit an enhanced sensitivity to ischemic lesions, i.e. ,60% change in sLD and,50% in DLD. These findings raised our interest in the following question: what are the advantages of other non-Gaussian models suggested in the literature and how they will perform in the assessment of stroke in comparison to each other? In this work we provide a characterisation of the ischemic lesions in animals by three nonGaussian models: a) stretched exponential model (SEM), b) the statistical model based on the gamma distribution function (GDF), and c) biexponential diffusion tensor analysis (BEDTA)
Typical diffusion attenuation curves for two representative voxels located in healthy and affected regions are shown in Figures 2a–2c, together with their fits using gamma-distribution function (GDF), SEM and BEDTA, respectively
Summary
Diffusion magnetic resonance imaging (MRI) is known as an important tool in early diagnostics and assessment of stroke [1,2]. The apparent diffusion coefficient (ADC) exhibits a strong reduction within the first half an hour after the onset of infarction and allows for a visualisation of the ischemic lesion prior to manifestation by other conventional MRI modalities. In spite of the high clinical relevance and intensive studies, the biophysical mechanisms of the observed ADC reduction are not yet well understood [3]. They are most frequently ascribed to the combined effects of restricting more water in swollen cells and an increased tortuosity of the extracellular space. More recent studies suggest focal enlargements of cellular projections (the so-called neurite beading) [8,9,10] as an essential mechanism of decreasing the diffusion coefficient
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
