aiqbench analysis
SC-TauPath introduces a novel framework that bridges structural connectivity analysis with tau propagation modeling in Alzheimer's disease by leveraging gradient-based attribution to generate interpretable pathway maps. The method successfully validates established Braak staging anatomy using real-world neuroimaging data from 234 participants, offering a biologically grounded alternative to models reliant on heavy biophysical assumptions. This approach provides a significant step forward for researchers seeking neurobiologically interpretable tools to map disease progression without over-reliance on theoretical constraints.
SC-TauPath: A Structural Connectivity Attribution Framework for Mapping Tau Propagation Pathways in Alzheimer's Disease
arXiv:2606.04066v1 Announce Type: cross Abstract: Understanding how structural connections are associated with tau propagation in Alzheimer's disease (AD) remains a central open question, yet existing computational models either rely heavily on biophysical assumptions or lack neurobiologically interpretable pathway maps. We present SC-TauPath, a structural connectivity (SC) attribution framework that maps tau propagation pathways from in vivo neuroimaging data. SC-TauPath combines a Network Diffusion Model (NDM)-augmented multilayer perceptron with gradient $\times$ input attribution to score each SC edge's contribution to tau prediction, then translates these attribution scores into multi-scale pathway maps (backbone edges, high-traffic routes, and hub ROIs), which validates established Braak staging anatomy. Applied to 234 ADNI participants with paired DTI SC and 18F-Flortaucipir PET, SC-TauPath achieves strong cross-validated tau prediction and yields attribution-based pathway maps consistent with established Braak staging anatomy, demonstrating that SC encode spatially specific information about regional tau distribution in AD.
Abstract:Understanding how structural connections are associated with tau propagation in Alzheimer's disease (AD) remains a central open question, yet existing computational models either rely heavily on biophysical assumptions or lack neurobiologically interpretable pathway maps. We present SC-TauPath, a structural connectivity (SC) attribution framework that maps tau propagation pathways from in vivo neuroimaging data. SC-TauPath combines a Network Diffusion Model (NDM)-augmented multilayer perceptron with gradient $\times$ input attribution to score each SC edge's contribution to tau prediction, then translates these attribution scores into multi-scale pathway maps (backbone edges, high-traffic routes, and hub ROIs), which validates established Braak staging anatomy. Applied to 234 ADNI participants with paired DTI SC and 18F-Flortaucipir PET, SC-TauPath achieves strong cross-validated tau prediction and yields attribution-based pathway maps consistent with established Braak staging anatomy, demonstrating that SC encode spatially specific information about regional tau distribution in AD.
Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG)
arXiv:2606.04066 [q-bio.NC]
(or arXiv:2606.04066v1 [q-bio.NC] for this version)
https://doi.org/10.48550/arXiv.2606.04066 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 236 words
Related coverage
LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
arXiv · Oct 10, 2026
DAAF: From Failure Localization to Editable System Assets in LLM Agents
arXiv · Sep 29, 2026
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
arXiv · Oct 21, 2026
MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributes
arXiv · Sep 1, 2026