Related Experiment Video
Updated: Jun 29, 2025
12:28
Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains
Published on: June 3, 2020
17.3K
Distinct spatiotemporal atrophy patterns in corticobasal syndrome are associated with different underlying
W J Scotton1, C Shand2, E G Todd1
1Dementia Research Centre, Department of Neurodegenerative Disease, University College London Queen Square Institute of Neurology, University College London, London, UK.
Medrxiv : the Preprint Server for Health Sciences
|April 2, 2024
Summary
Machine learning identified two distinct MRI atrophy subtypes in corticobasal syndrome (CBS). These subtypes correlate with specific underlying pathologies, aiding in clinical trial screening and disease progression tracking.
Area of Science:
- Neuroimaging
- Neurology
- Machine Learning
Background:
- Corticobasal syndrome (CBS) presents diagnostic challenges due to heterogeneous presentations.
- Identifying distinct imaging subtypes is crucial for understanding underlying pathologies and guiding treatment.
Approach:
- Applied Subtype and Stage Inference (SuStaIn), a machine learning algorithm, to MRI volumetric data from 135 CBS cases and 252 controls.
- Validated the model using follow-up MRI scans to assess subtype stability and disease progression.
- Compared clinical phenotypes and associated pathologies across identified subtypes.
Key Points:
- SuStaIn identified two stable atrophy progression subtypes: 'Subcortical' and 'Fronto-parieto-occipital'.
- The 'Subcortical' subtype was associated with four-repeat-tauopathies (CBS-PSP, CBS-CBD).
- The 'Fronto-parieto-occipital' subtype was predominantly linked to CBS-AD.
- Subtype assignment demonstrated high stability (98%) at follow-up, with consistent progression through disease stages.
Conclusions:
- Provides data-driven evidence for at least two distinct, longitudinally stable spatiotemporal atrophy subtypes in CBS.
- These subtypes are associated with different underlying pathologies, offering insights beyond current biomarkers.
- Accurate subtyping and staging at baseline are vital for clinical trial recruitment and monitoring disease progression in CBS.
