NeuroImage
-
Multicenter Study
Predicting symptom severity in autism spectrum disorder based on cortical thickness measures in agglomerative data.
Machine learning approaches have been widely used for the identification of neuropathology from neuroimaging data. However, these approaches require large samples and suffer from the challenges associated with multi-site, multi-protocol data. We propose a novel approach to address these challenges, and demonstrate its usefulness with the Autism Brain Imaging Data Exchange (ABIDE) database. ⋯ The proposed approach consists of two main stages: a domain adaptation stage using partial least squares regression to maximize the consistency of imaging data across sites; and a learning stage combining support vector regression for regional prediction of severity with elastic-net penalized linear regression for integrating regional predictions into a whole-brain severity prediction. The proposed method performed markedly better than simpler alternatives, better with multi-site than single-site data, and resulted in a considerably higher cross-validated correlation score than has previously been reported in the literature for multi-site data. This demonstration of the utility of the proposed approach for detecting structural brain abnormalities in ASD from the multi-site, multi-protocol ABIDE dataset indicates the potential of designing machine learning methods to meet the challenges of agglomerative data.
-
Comparative Study
Diffusion kurtosis metrics as biomarkers of microstructural development: A comparative study of a group of children and a group of adults.
The most common modality of diffusion MRI used in the ageing and development studies is diffusion tensor imaging (DTI) providing two key measures, fractional anisotropy and mean diffusivity. Here, we investigated diffusional changes occurring between childhood (average age 10.3 years) and mitddle adult age (average age 54.3 years) with the help of diffusion kurtosis imaging (DKI), a recent novel extension of DTI that provides additional metrics quantifying non-Gaussianity of water diffusion in brain tissue. We performed voxelwise statistical between-group comparison of diffusion tensor and kurtosis tensor metrics using two methods, namely, the tract-based spatial statistics (TBSS) and the atlas-based regional data analysis. ⋯ The largest changes of this parameter (interpreted as reflecting the lowest level of maturation by the age of children group) were observed in the association fibres, cingulum (gyrus) and cingulum (hippocampus) followed by superior longitudinal fasciculus and inferior longitudinal fasciculus. The smallest changes were observed in the commissural fibres, forceps major and forceps minor. In conclusion, our data suggest that DKI is sensitive to developmental changes in local microstructure and environment, and is particularly powerful to unravel developmental differences in major association fibres, such as the cingulum and superior longitudinal fasciculus.