TractSpLearn: Specialized Shared-Manifold Learning for Individualized Detection of Subtle White Matter Alterations in Mild Traumatic Brain Injury
Abstract
Traumatic brain injury (TBI) often leads to subtle white matter damage that remains undetected on conventional MRI. Diffusion kurtosis imaging (DKI), an extension of diffusion tensor imaging (DTI), provides complementary information on non-Gaussian water diffusion and is sensitive to complex white-matter microstructure. With the advent of ultra-high-field MRI, the spatial resolution and signal-to-noise ratios (SNR) have been significantly enhanced, enabling more precise visualization of subtle abnormalities. Building on these advances, we developed TractSpLearn, an individualized tract-based learning framework that jointly considers within-group variability and between-group differences. Unlike the original TractLearn framework, which learns a normative manifold exclusively from healthy controls, TractSpLearn incorporates both healthy controls and patients to learn a shared manifold with a healthy-anchored representation and an additional patient-related component. To assess the performance of the proposed method, we compared TractSpLearn with the original TractLearn in three cohorts: (i) healthy controls (HC), (ii) athletes with persistent post-concussive syndromes (PPCS), and (iii) athletes with repeated head injuries (RHI), with abnormalities particularly evident in axial kurtosis (AK) and mean diffusivity (MD). In RHI, TractSpLearn highlighted recurrent abnormalities across patients. In the PPCS cohort, the overall group-level differences were more modest, potentially reflecting both limited statistical power due to the small sample size and partial normalization of white-matter alterations during recovery. Still TractSpLearn identified abnormality evidence in more patients and across more affected tracts than TractLearn.
Related
- Detection of acquired TERT amplification in addition to predisposing p53 and Rb pathways alterations in EGFR-mutant lung adenocarcinomas transformed into small-cell lung cancers.
- Generalized pollination of morphologically specialized Vincetoxicum hirundinaria (Apocynaceae, Asclepiadoideae)
- Mitotic centromeres organize in repeat-subunits with specialized histone landscape and multi-domain architecture as revealed by expansion microscopy
- The bacterial pathogen causing cucurbit yellow vine disease associates with the specialized extrafascicular phloem unique to cucurbits
- EcoHIV Treated Primary Microglia Exhibit a Highly Specialized and Sex-Dependent Transcriptional State
BibTeX
@misc{huang2026tractsplearn,
title = {{TractSpLearn: Specialized Shared-Manifold Learning for Individualized Detection of Subtle White Matter Alterations in Mild Traumatic Brain Injury}},
author = {Jiqing Huang and Ali Al-Husseini and Yi Chen and Anna Gard and Laurent Lamalle and Mohamed Ali Bahri and Markus Nilsson and Niklas Marklund and Christophe Phillips and Evgenios N. Kornaropoulos},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15342},
eprint = {2609.15342},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15342},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - TractSpLearn: Specialized Shared-Manifold Learning for Individualized Detection of Subtle White Matter Alterations in Mild Traumatic Brain Injury
AU - Jiqing Huang
AU - Ali Al-Husseini
AU - Yi Chen
AU - Anna Gard
AU - Laurent Lamalle
AU - Mohamed Ali Bahri
AU - Markus Nilsson
AU - Niklas Marklund
AU - Christophe Phillips
AU - Evgenios N. Kornaropoulos
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15342
UR - https://arxiv.org/abs/2609.15342
AB - Traumatic brain injury (TBI) often leads to subtle white matter damage that remains undetected on conventional MRI. Diffusion kurtosis imaging (DKI), an extension of diffusion tensor imaging (DTI), provides complementary information on non-Gaussian water diffusion and is sensitive to complex white-matter microstructure. With the advent of ultra-high-field MRI, the spatial resolution and signal-to-noise ratios (SNR) have been significantly enhanced, enabling more precise visualization of subtle abnormalities. Building on these advances, we developed TractSpLearn, an individualized tract-based learning framework that jointly considers within-group variability and between-group differences. Unlike the original TractLearn framework, which learns a normative manifold exclusively from healthy controls, TractSpLearn incorporates both healthy controls and patients to learn a shared manifold with a healthy-anchored representation and an additional patient-related component. To assess the performance of the proposed method, we compared TractSpLearn with the original TractLearn in three cohorts: (i) healthy controls (HC), (ii) athletes with persistent post-concussive syndromes (PPCS), and (iii) athletes with repeated head injuries (RHI), with abnormalities particularly evident in axial kurtosis (AK) and mean diffusivity (MD). In RHI, TractSpLearn highlighted recurrent abnormalities across patients. In the PPCS cohort, the overall group-level differences were more modest, potentially reflecting both limited statistical power due to the small sample size and partial normalization of white-matter alterations during recovery. Still TractSpLearn identified abnormality evidence in more patients and across more affected tracts than TractLearn.
ER -