Abstract

White matter (WM) serves as a fundamental component of the brain providing essential structural support and facilitating the brain cognitive processes. Thus, an accurate and efficient description of the brain's white matter structure is essential for understanding brain function connectivity and development. In this work we used the deep model to combine the information of the WM fiber bundle shape and its related cortical folding patterns together representing the WM fiber bundle from diffusion MRI tractography into a pre-defined low-dimensional space and generate the numerical representation vector. This cortical-aware vector-quantized variational encoder (CA-VQVAE) framework leverages cortical locations and folding patterns to ameliorate the description of fiber bundle structures mitigating measurement uncertainty and individual variability. The numerical representation of the WM structure captured the morphological characteristics, which enabled the identification of cross-subject correspondence and precise comparison numerical comparison of fiber bundles. The testing results demonstrated cross-subject consistency in downstream tasks.

Department(s)

Computer Science

Comments

National Institutes of Health, Grant R01AG075582

Keywords and Phrases

Contrastive learning; Diffusion imaging; Morphology; Vector Quantize; White matter

International Standard Serial Number (ISSN)

1945-8452; 1945-7928

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Jan 2025

Download

Full Text Link

Share

 
COinS