Structural parameters are superior to eigenvector centrality in detecting progressive supranuclear palsy with machine learning & multimodal MRI

Keyphrases

• Machine Learning 100%
• Progressive Supranuclear Palsy 100%
• Multimodal MRI 100%
• Eigenvector Centrality 100%
• Midbrain 50%
• Anterior Cingulate Cortex 25%
• Eye Movements 25%
• Cerebellum 25%
• Healthy Controls 25%
• Brain Structure 25%
• T1-weighted 25%
• Machine Learning Approach 25%
• Insula 25%
• Cerebellar Peduncles 25%
• Feature Selection 25%
• Disease-specific 25%
• Multimodal Imaging 25%
• Atypical Parkinsonian Syndromes 25%
• Imaging Studies 25%
• Multicentric 25%
• Centrality Measures 25%
• Movement Impairment 25%
• Resting-state Functional Magnetic Resonance Imaging (rs-fMRI) 25%
• Brain Alterations 25%
• Brain Changes 25%
• White Matter Volume 25%
• Centrality Analysis 25%
• Functional Disease 25%
• Gray Matter Volume 25%
• Brainstem Atrophy 25%
• Grey Matter Segmentation 25%
• Multivariate Pattern Classification 25%
• White Matter Segmentation 25%
• Temporal Gyrus 25%
• Centrality Parameters 25%
• Structural Disease 25%

Medicine and Dentistry

• Magnetic Resonance Imaging 100%
• Progressive Supranuclear Palsy 100%
• Midbrain 75%
• Gray Matter 50%
• Cingulate Cortex 25%
• Eye Movement 25%
• Functional Disease 25%
• Parkinsonism 25%
• Cerebellum 25%
• Functional Magnetic Resonance Imaging 25%
• Multimodal Imaging 25%
• Pattern Recognition 25%
• Insula 25%
• Cerebellar Peduncle 25%
• Temporal Gyrus 25%
• Feature Extraction 25%

Neuroscience

• Magnetic Resonance Imaging 100%
• Progressive Supranuclear Palsy 100%
• Midbrain 75%
• Gray Matter 50%
• Cerebellum 25%
• Eye Movement 25%
• Gyri 25%
• Cingulate Cortex 25%
• Functional Magnetic Resonance Imaging 25%
• Parkinsonism 25%
• Pattern Recognition 25%