Deep Learning-Based Regional White Matter Hyperintensity Mapping as a Robust Biomarker for Alzheimer's Disease

2025-11-18

AI Summary

Existing automated white matter hyperintensity (WMH) segmentation methods typically yield only global lesion burden, neglecting spatially localized distribution patterns—limiting their clinical utility in Alzheimer’s disease (AD) diagnosis. To address this, we propose a deep learning–based framework for region-specific WMH segmentation and quantitative analysis: first performing high-accuracy, voxel-wise WMH segmentation; then computing regional lesion burdens according to anatomically defined white matter tracts (e.g., anterior pathways); and finally integrating these with structural MRI biomarkers (e.g., hippocampal atrophy) in a multimodal predictive model. Our key contribution is the first systematic demonstration that region-specific WMH burden—particularly in anterior white matter tracts—exhibits stronger association with AD status than global burden. Experimental results show that combining regional WMH burden with brain atrophy features achieves an AD classification AUC of 0.97, significantly enhancing diagnostic performance.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

White matter hyperintensities (WMH) are key imaging markers in cognitive aging, Alzheimer's disease (AD), and related dementias. Although automated methods for WMH segmentation have advanced, most provide only global lesion load and overlook their spatial distribution across distinct white matter regions. We propose a deep learning framework for robust WMH segmentation and localization, evaluated across public datasets and an independent Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our results show that the predicted lesion loads are in line with the reference WMH estimates, confirming the robustness to variations in lesion load, acquisition, and demographics. Beyond accurate segmentation, we quantify WMH load within anatomically defined regions and combine these measures with brain structure volumes to assess diagnostic value. Regional WMH volumes consistently outperform global lesion burden for disease classification, and integration with brain atrophy metrics further improves performance, reaching area under the curve (AUC) values up to 0.97. Several spatially distinct regions, particularly within anterior white matter tracts, are reproducibly associated with diagnostic status, indicating localized vulnerability in AD. These results highlight the added value of regional WMH quantification. Incorporating localized lesion metrics alongside atrophy markers may enhance early diagnosis and stratification in neurodegenerative disorders.

Problem

• Mapping white matter hyperintensities across brain regions for Alzheimer's disease diagnosis
• Overcoming limitations of global lesion load by analyzing spatial distribution patterns
• Combining regional WMH volumes with brain atrophy metrics to improve classification

Innovation

• Deep learning framework for WMH segmentation and localization
• Quantifying WMH load within anatomically defined brain regions
• Combining regional WMH volumes with brain atrophy metrics