A totally data-driven whole-brain multimodal pipeline for the discrimination of Parkinson's disease, multiple system atrophy and healthy control.

Parkinson's Disease (PD) and Multiple System Atrophy (MSA) are two parkinsonian syndromes that share many symptoms, albeit having very different prognosis. Although previous studies have proposed multimodal MRI protocols combined with multivariate analysis to discriminate between these two populations and healthy controls, studies combining all MRI indexes relevant for these disorders (i.e. grey matter volume, fractional anisotropy, mean diffusivity, iron deposition, brain activity at rest and brain connectivity) with a completely data-driven voxelwise analysis for discrimination are still lacking. In this study, we used such a complete MRI protocol and adapted a fully-data driven analysis pipeline to discriminate between these populations and a healthy controls (HC) group. The pipeline combined several feature selection and reduction steps to obtain interpretable models with a low number of discriminant features that can shed light onto the brain pathology of PD and MSA. Using this pipeline, we could discriminate between PD and HC (best accuracy = 0.78), MSA and HC (best accuracy = 0.94) and PD and MSA (best accuracy = 0.88). Moreover, we showed that indexes derived from resting-state fMRI alone could discriminate between PD and HC, while mean diffusivity in the cerebellum and the putamen alone could discriminate between MSA and HC. On the other hand, a more diverse set of indexes derived by multiple modalities was needed to discriminate between the two disorders. We showed that our pipeline was able to discriminate between distinct pathological populations while delivering sparse model that could be used to better understand the neural underpinning of the pathologies.

MRI measures of corpus callosum iron and myelin in early Huntington's disease.

Increased iron in subcortical gray matter (GM) structures of patients with Huntington's disease (HD) has been suggested as a causal factor in neuronal degeneration. But how iron content is related to white matter (WM) changes in HD is still unknown. For example, it is not clear whether WM changes share the same physiopathology (i.e. iron accumulation) with GM or whether there is a different mechanism. The present study used MRI to examine iron content in premanifest gene carriers (PreHD, n = 25) and in early HD patients (n = 25) compared with healthy controls (n = 50). 3T MRI acquisitions included high resolution 3D T1, EPI sequences for diffusion tensor imaging (DTI) as an indirect measure of tissue integrity, and T2*-weighted gradient echo-planar imaging for MR-based relaxometry (R2*), which provides an indirect measure of ferritin/iron deposition in the brain. Myelin breakdown starts in the PreHD stage, but there is no difference in iron content values. Iron content reduction manifests later, in the early HD stage, in which we found a lower R2* parameter value in the isthmus. The WM iron reduction in HD is temporally well-defined (no iron differences in PreHD subjects and iron differences only in early HD patients). Iron level in callosal WM may be regarded as a marker of disease state, as iron does not differentiate PreHD subjects from controls but distinguishes between PreHD and HD.