Modelling the distribution of white matter hyperintensities due to ageing on MRI images using Bayesian inference

Abstract

White matter hyperintensities (WMH), also known as white matter lesions, are localised white matter areas that appear hyperintense on MRI scans. WMH commonly occur in the ageing population, and are often associated with several factors such as cognitive disorders, cardiovascular risk factors, cerebrovascular and neurodegenerative diseases. Despite the fact that some links between lesion location and parametric factors such as age have already been established, the relationship between voxel-wise spatial distribution of lesions and these factors is not yet well understood. Hence, it would be of clinical importance to model the distribution of lesions at the population-level and quantitatively analyse the effect of various factors on the lesion distribution model.In this work we compare various methods, including our proposed method, to generate voxel-wise distributions of WMH within a population with respect to various factors. Our proposed Bayesian spline method models the spatio-temporal distribution of WMH with respect to a parametric factor of interest, in this case age, within a population. Our probabilistic model takes as input the lesion segmentation binary maps of subjects belonging to various age groups and provides a population-level parametric lesion probability map as output. We used a spline representation to ensure a degree of smoothness in space and the dimension associated with the parameter, and formulated our model using a Bayesian framework.We tested our algorithm output on simulated data and compared our results with those obtained using various existing methods with different levels of algorithmic and computational complexity. We then compared the better performing methods on a real dataset, consisting of 1000 subjects of the UK Biobank, divided in two groups based on hypertension diagnosis. Finally, we applied our method on a clinical dataset of patients with vascular disease.On simulated dataset, the results from our algorithm showed a mean square error (MSE) value of 7.27×10−5, which was lower than the MSE value reported in the literature, with the advantage of being robust and computationally efficient. In the UK Biobank data, we found that the lesion probabilities are higher for the hypertension group compared to the non-hypertension group and further verified this finding using a statistical t-test. Finally, when applying our method on patients with vascular disease, we observed that the overall probability of lesions is significantly higher in later age groups, which is in line with the current literature.

Correlation between 24-Hour Ambulatory Blood Pressure Variability and White Matter Lesions in Patients with Cerebral Small Vascular Disease: A Cross-Sectional Study

“…Age has been identified as an independent risk factor for periventricular WML in British and American populations [ 16 , 17 ]. Also, intracranial small vascular atherosclerosis progresses with age.…”

Voxel-wise and spatial modelling of binary lesion masks: Comparison of methods with a realistic simulation framework

“…Age is used as the sole regressor and by using a reference data set, we start building our simulation study by setting the true age coefficient map to the UKB-derived one. In other simulation studies, binary lesion masks or 2D slices are simulated, but the true coefficients are not available (Sundaresan et al, 2019; Ge et al, 2014), which does not allow any comparison between competing methods.…”

Voxel-wise and spatial modelling of binary lesion masks: Comparison of methods with a realistic simulation framework

“…Age is used as the sole regressor and by using a reference data set, we start building our simulation study by setting the true age coefficient map to the UKB-derived one. In other simulation studies, binary lesion masks or 2D slices are simulated, but the true coefficients are not available ( Ge, Müller-Lenke, Bendfeldt, Nichols, Johnson, 2014 , Sundaresan, Griffanti, Kindalova, Alfaro-Almagro, Zamboni, Rothwell, Nichols, Jenkinson, 2019 ), which does not allow any comparison between competing methods.…”

“…We made the artificial lesion masks as realistic as possible through tuning to make sure the artificial and real lesion masks share important lesion characteristics, such as lesion size, lesion count and lesion volume. This step potentially overcomes the drawbacks of other simulation approaches, where the same count, size and shape lesions are simulated (6 spheroid lesions of size 5 voxels in each dimension, Chard et al., 2010 ) or smoothing of the resulting simulated lesion masks ( Sundaresan et al., 2019 ) is applied, which could introduce stronger spatial dependencies than what is expected from real lesion masks.…”