View in EDS

Large-scale modeling of axonal dynamic responses via deep learning.

Saved in:

Bibliographic Details
Title:	Large-scale modeling of axonal dynamic responses via deep learning.
Authors:	Zhang, Chaokai¹ (AUTHOR), Clansey, Adam² (AUTHOR), Bartels, Lara³ (AUTHOR), Bondi, Daniel² (AUTHOR), Kloiber, Julian³ (AUTHOR), Jaffray, Alexander³ (AUTHOR), van Donkelaar, Paul⁴ (AUTHOR), Rauscher, Alexander³ (AUTHOR), Wu, Lyndia² (AUTHOR), Ji, Songbai^1,5 (AUTHOR) sji@wpi.edu
Source:	Biomechanics & Modeling in Mechanobiology. Feb2026, Vol. 25 Issue 1, p1-19. 19p.
Abstract:	Large-scale axonal dynamic simulation is critical to study white matter injury but is prohibitive in computational cost. We solve this challenge by training a convolutional neural network (CNN) that takes fiber strain profiles as inputs to instantly estimate multimodal axonal injury parameters. First, tractography-based fiber strains are derived based on subject-specific simulations of N = 46 head impacts from a male ice hockey player. To generate the minimum training dataset, the brain is subdivided into coarse cubes (isotropic resolution of 6 mm; N = 4979 voxels). A stratified (one sample per cube) and adaptive (by controlling a similarity threshold) sampling strategy is devised to iteratively identify the most distinct profiles from N = 45 head impacts used for training (with the remaining one reserved for independent validation). They serve as the input to a male axonal injury model for simulation. A CNN is then trained to estimate the peak strains in microtubule and axolemma as well as the failure percentages of tau proteins and neurofilaments. The CNN is cross-validated to determine the minimum training samples of N = 2000 to reach R 2 >0.90. Under the “worst case scenario” for independent validation (N = 75 testing samples identified), the CNN achieves an R 2 of 0.91–0.98 and a normalized root mean-squared error (NRMSE) of 2.7–5.0%. Finally, we showcase the CNN by generating high-resolution multimodal axonal responses for the entire white matter within 12 s (isotropic resolution of 2 mm with ~ 92,500 voxels), vs. an estimated ~ 12 years using conventional direct simulations (~ 31.5-million-fold efficiency gain). This study demonstrates the potential of deep learning to enable large-scale mechanistic investigations of white matter injury in the future. [ABSTRACT FROM AUTHOR]
	Copyright of Biomechanics & Modeling in Mechanobiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Large-scale axonal dynamic simulation is critical to study white matter injury but is prohibitive in computational cost. We solve this challenge by training a convolutional neural network (CNN) that takes fiber strain profiles as inputs to instantly estimate multimodal axonal injury parameters. First, tractography-based fiber strains are derived based on subject-specific simulations of N = 46 head impacts from a male ice hockey player. To generate the minimum training dataset, the brain is subdivided into coarse cubes (isotropic resolution of 6 mm; N = 4979 voxels). A stratified (one sample per cube) and adaptive (by controlling a similarity threshold) sampling strategy is devised to iteratively identify the most distinct profiles from N = 45 head impacts used for training (with the remaining one reserved for independent validation). They serve as the input to a male axonal injury model for simulation. A CNN is then trained to estimate the peak strains in microtubule and axolemma as well as the failure percentages of tau proteins and neurofilaments. The CNN is cross-validated to determine the minimum training samples of N = 2000 to reach R 2 >0.90. Under the “worst case scenario” for independent validation (N = 75 testing samples identified), the CNN achieves an R 2 of 0.91–0.98 and a normalized root mean-squared error (NRMSE) of 2.7–5.0%. Finally, we showcase the CNN by generating high-resolution multimodal axonal responses for the entire white matter within 12 s (isotropic resolution of 2 mm with ~ 92,500 voxels), vs. an estimated ~ 12 years using conventional direct simulations (~ 31.5-million-fold efficiency gain). This study demonstrates the potential of deep learning to enable large-scale mechanistic investigations of white matter injury in the future. [ABSTRACT FROM AUTHOR]
ISSN:	16177959
DOI:	10.1007/s10237-025-02034-6