Alzheimer's Imaging Consortium.

Area of Science:

• Neurology
• Neuroimaging
• Gerontology

Background:

• Limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC) is a common finding in aging brains, but definitive diagnosis requires autopsy.
• Current diagnostic limitations hinder timely intervention and research for LATE-NC.

Purpose of the Study:

• To develop and validate an in-vivo magnetic resonance imaging (MRI) marker for LATE-NC.
• To create an automated tool for LATE-NC diagnosis using neuroimaging features.

Main Methods:

• Utilized ex-vivo and in-vivo MRI data alongside pathology from longitudinal aging studies.
• Developed a two-level stacking classifier using fractional anisotropy, deformation-based morphometry, and lobar volumes.
• Packaged the classifier into an automated software container named MARBLE (MARker of Brain LatE).

Main Results:

• The ex-vivo classifier achieved an AUC of 0.85, with 77% balanced accuracy.
• In-vivo validation of the MARBLE marker showed an AUC of 0.76.
• Higher MARBLE scores correlated significantly with advanced LATE-NC stages (p < 0.001).

Conclusions:

• MARBLE is a novel, automated, in-vivo MRI marker for LATE-NC.
• The tool demonstrated promising performance for in-vivo diagnosis and monitoring.
• Further validation in independent cohorts is necessary, but MARBLE holds potential for LATE-NC management.