Improved Multiscale Structural Mapping with Supervertex Vision Transformer for the Detection of Alzheimer's Disease Neurodegeneration

2026-04-16

AI Summary

This study addresses the urgent need for non-invasive biomarkers in Alzheimer’s disease (AD) diagnosis by leveraging routinely acquired T1-weighted MRI. The authors propose MSSM+, a novel method that integrates cortical thickness, gray-white matter contrast, sulcal depth, and curvature. By introducing Surface Super-Vertex Mapping (SSVM), the cortical surface is partitioned into super-vertices, enabling the design of a super-vertex vision Transformer (SV-ViT) tailored to cortical mesh data to model both intra- and inter-regional spatial relationships. Compared to the original MSSM, MSSM+ reveals more extensive and significant structural differences between AD patients and healthy controls, achieves a 3% improvement in AUPRC for classification tasks, and demonstrates reduced signal variability and enhanced stability across multi-vendor MRI datasets.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Alzheimer's disease (AD) confirmation often relies on positron emission tomography (PET) or cerebrospinal fluid (CSF) analysis, which are costly and invasive. Consequently, structural MRI biomarkers such as cortical thickness (CT) are widely used for non-invasive AD screening. Multiscale structural mapping (MSSM) was recently proposed to integrate gray-white matter contrasts (GWCs) with CT from a single T1-weighted MRI (T1w) scan. Building on this framework, we propose MSSM+, together with surface supervertex mapping (SSVM) and a Supervertex Vision Transformer (SV-ViT). 3D T1w images from individuals with AD and cognitively normal (CN) controls were analyzed. MSSM+ extends MSSM by incorporating sulcal depth and cortical curvature at the vertex level. SSVM partitions the cortical surface into supervertices (surface patches) that effectively represent inter- and intra-regional spatial relationships. SV-ViT is a Vision Transformer architecture operating on these supervertices, enabling anatomically informed learning from surface mesh representations. Compared with MSSM, MSSM+ identified more spatially extensive and statistically significant group differences between AD and CN. In AD vs. CN classification, MSSM+ achieved a 3%p higher area under the precision-recall curve than MSSM. Vendor-specific analyses further demonstrated reduced signal variability and consistently improved classification performance across MR manufacturers relative to CT, GWCs, and MSSM. These findings suggest that MSSM+ combined with SV-ViT is a promising MRI-based imaging marker for AD detection prior to CSF/PET confirmation.

Problem

• Alzheimer's disease
• structural MRI
• neurodegeneration
• biomarker
• non-invasive detection

Innovation

• Supervertex Vision Transformer
• Multiscale Structural Mapping
• Surface Supervertex Mapping
• Cortical Morphometry
• Alzheimer's Disease Biomarker