Disease-Specific Regions Outperform Whole-Brain Approaches in Identifying Progressive Supranuclear Palsy: A Multicentric MRI Study

To identify progressive supranuclear palsy (PSP), we combined voxel-based morphometry (VBM) and support vector machine (SVM) classification using disease-specific features in multicentric magnetic resonance imaging (MRI) data. Structural brain differences were investigated at four centers between 20...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neuroscience 2017-03, Vol.11, p.100-100
Main Authors: Mueller, Karsten, Jech, Robert, Bonnet, Cecilia, Tintěra, Jaroslav, Hanuška, Jaromir, Möller, Harald E, Fassbender, Klaus, Ludolph, Albert, Kassubek, Jan, Otto, Markus, Růžička, Evžen, Schroeter, Matthias L
Format: Article
Language:English
Subjects:
Accuracy
Age
Alzheimer's disease
Artificial intelligence
Atrophy
Brain stem
Classification
Dementia
Ethics
Hospitals
Machine learning
Magnetic resonance imaging
Meta-analysis
Morphometry
Neostriatum
Neural networks
Neuroimaging
Neurology
Neuroscience
NMR
Nuclear magnetic resonance
Paralysis
Parkinson's disease
Precision medicine
Progressive supranuclear palsy
Studies
Substantia grisea
Volumetric analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To identify progressive supranuclear palsy (PSP), we combined voxel-based morphometry (VBM) and support vector machine (SVM) classification using disease-specific features in multicentric magnetic resonance imaging (MRI) data. Structural brain differences were investigated at four centers between 20 patients with PSP and 20 age-matched healthy controls with T1-weighted MRI at 3T. To pave the way for future application in personalized medicine, we applied SVM classification to identify PSP on an individual level besides group analyses based on VBM. We found a major decline in gray matter density in the brainstem, insula, and striatum, and also in frontomedian regions, which is in line with current literature. Moreover, SVM classification yielded high accuracy rates above 80% for disease identification in imaging data. Focusing analyses on disease-specific regions-of-interest (ROI) led to higher accuracy rates compared to a whole-brain approach. Using a polynomial kernel (instead of a linear kernel) led to an increased sensitivity and a higher specificity of disease detection. Our study supports the application of MRI for individual diagnosis of PSP, if combined with SVM approaches. We demonstrate that SVM classification provides high accuracy rates in multicentric data-a prerequisite for potential application in diagnostic routine.
ISSN:1662-4548
1662-453X
1662-453X
DOI:10.3389/fnins.2017.00100