Widespread diffusion changes differentiate Parkinson's disease and progressive supranuclear palsy

• Published in: NeuroImage clinical Vol. 20; pp. 1037 - 1043
• Main Authors: Talai, Aron S., Sedlacik, Jan, Boelmans, Kai, Forkert, Nils D.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.01.2018; Elsevier
• Subjects: Adult; Aged; Brain Stem - pathology; Computer-Assisted Image Analysis; Diffusion Magnetic Resonance Imaging - methods; Diffusion Tensor Imaging - methods; Diffusion-tensor magnetic resonance imaging; Female; Gray Matter - pathology; Humans; Image Processing, Computer-Assisted - methods; Male; Middle Aged; Parkinson Disease - diagnosis; Parkinson Disease - pathology; Parkinson's disease; Progressive supranuclear palsy; Radiology; Regular; Support vector machines; Supranuclear Palsy, Progressive - diagnosis; Supranuclear Palsy, Progressive - pathology; Parkinson's disease; AD; Diffusion-tensor magnetic resonance imaging; ROC; MNI; Support vector machines; RD; Computer-Assisted Image Analysis; PD; Progressive supranuclear palsy; MD; UPDRS; HC; PSP-RS; FA; radial diffusivity; unified Parkinson's disease rating scale; Montreal Neurological Institute; progressive supranuclear palsy – Richardson's syndrome; fractional anisotropy; axial diffusivity; receiver operating characteristic; healthy control; mean diffusivity
• ISSN: 2213-1582; 2213-1582
• DOI: 10.1016/j.nicl.2018.09.028

Parkinson's disease (PD) and progressive supranuclear palsy – Richardson's syndrome (PSP-RS) are often represented by similar clinical symptoms, which may challenge diagnostic accuracy. The objective of this study was to investigate and compare regional cerebral diffusion properties in PD and PSP-RS subjects and evaluate the use of these metrics for an automatic classification framework. Diffusion-tensor MRI datasets from 52 PD and 21 PSP-RS subjects were employed for this study. Using an atlas-based approach, regional median values of mean diffusivity (MD), fractional anisotropy (FA), radial diffusivity (RD), and axial diffusivity (AD) were measured and employed for feature selection using RELIEFF and subsequent classification using a support vector machine. According to RELIEFF, the top 17 diffusion values consisting of deep gray matter structures, the brainstem, and frontal cortex were found to be especially informative for an automatic classification. A MANCOVA analysis performed on these diffusion values as dependent variables revealed that PSP-RS and PD subjects differ significantly (p < .001). Generally, PSP-RS subjects exhibit reduced FA, and increased MD, RD, and AD values in nearly all brain structures analyzed compared to PD subjects. The leave-one-out cross-validation of the support vector machine classifier revealed that the classifier can differentiate PD and PSP-RS subjects with an accuracy of 87.7%. More precisely, six PD subjects were wrongly classified as PSP-RS and three PSP-RS subjects were wrongly classified as PD. The results of this study demonstrate that PSP-RS subjects exhibit widespread and more severe diffusion alterations compared to PD patients, which appears valuable for an automatic computer-aided diagnosis approach. •Brain diffusion was compared in progressive supranuclear palsy-Richardson's syndrome (PSP-RS) and Parkinson's disease (PD).•Results show widespread diffusion alterations in PSP-RS compared to PD.•PSP-RS patients show significant reduction of FA and an increase of MD, RD, and AD values in compared to PD.•RELIEFF feature selection combined with a support vector machine classifier resulted in a differentiation accuracy of 87.7%.