Skip to main content

Medical-image Analysis and Statistical Interpretation Lab

Brain age identification from diffusion MRI synergistically predicts neurodegenerative disease

Posted by on Monday, December 8, 2025 in Brain Age, Deep Learning, Diffusion Weighted MRI.

Chenyu Gao, Michael E Kim, Karthik Ramadass, Praitayini Kanakaraj, Aravind R Krishnan, Adam M Saunders, Nancy R Newlin, Ho Hin Lee, Qi Yang, Warren D Taylor, Brian D Boyd, Lori L Beason-Held, Susan M Resnick, Lisa L Barnes, David A Bennett, Marilyn S Albert, Katherine D Van Schaik, Derek B Archer, Timothy J Hohman, Angela L Jefferson, Ivana Išgum, Daniel Moyer, Yuankai Huo, Kurt G Schilling, Lianrui Zuo, Shunxing Bao, Nazirah Mohd Khairi, Zhiyuan Li, Christos Davatzikos, Bennett A Landman. “Brain age identification from diffusion MRI synergistically predicts neurodegenerative disease”. Imaging Neuroscience 3, imag_a_00552. https://doi.org/10.1162/imag_a_00552

GitHub: https://github.com/MASILab/BRAID

Singularity: https://zenodo.org/records/15091613

Abstract

Estimated brain age from magnetic resonance image (MRI) and its deviation from chronological age can provide early insights into potential neurodegenerative diseases, supporting early detection and implementation of prevention strategies to slow disease progression and onset. Diffusion MRI (dMRI), a widely used modality for brain age estimation, presents an opportunity to build an earlier biomarker for neurodegenerative disease prediction because it captures subtle microstructural changes that precede more perceptible macrostructural changes. However, the coexistence of macro- and micro-structural information in dMRI raises the question of whether current dMRI-based brain age estimation models are leveraging the intended microstructural information or if they inadvertently rely on the macrostructural information. To develop a microstructure-specific brain age, we propose a method for brain age identification from dMRI that mitigates the model’s use of macrostructural information by non-rigidly registering all images to a standard template. Imaging data from 13,398 participants across 12 datasets were used for the training and evaluation. We compare our brain age models, trained with and without macrostructural information mitigated, with an architecturally similar T1-weighted (T1w) MRI-based brain age model and two recent, popular, openly available T1w MRI-based brain age models that primarily use macrostructural information. We observe difference between our dMRI-based brain age and T1w MRI-based brain age across stages of neurodegeneration, with dMRI-based brain age being older than T1w MRI-based brain age in participants transitioning from cognitively normal (CN) to mild cognitive impairment (MCI) (p-value = 0.023), but younger in participants already diagnosed with Alzheimer’s disease (AD) (p-value < 0.001). Classifiers using T1w MRI-based brain ages generally outperform those using dMRI-based brain age in classifying CN versus AD participants. Conversely, dMRI-based brain age may offer advantages over T1w MRI-based brain age in predicting the transition from CN to MCI.

Brain age estimation frameworks have proven effective for using affinely aligned brain images to identify common patterns of aging, with deviations from these patterns likely indicating presence of abnormal neuropathologic processes. A common theme of existing brain age estimation methods has been using T1w MRI, denoted as “GM age” in the first row. Among them, there have been many innovations in network design, such as DeepBrainNet (DBN) (Bashyam et al., 2020) and the 3D convolutional neural network of TSAN (Cheng et al., 2021). T1w MRI lacks detail in white matter (WM). Here, we take the two most commonly used modalities for characterizing WM microstructure, fractional anisotropy (FA), and mean diffusivity (MD), and we evaluate brain age estimation in two contexts. First, we examine the direct substitution of FA and MD for T1w image, which we denote as “WM age affine” in the second row. A substantial amount of macrostructural differences is still present in WM age affine, notably ventricle enlargement. To isolate the microstructural changes, we apply non-rigid (deformable) registration into template space to mitigate the macrostructural changes and produce the “WM age nonrigid” in the third row. We explore the relative timing of changes in these brain age variants and their relative explainability in the context of mild cognitive impairment. Throughout the paper, we adhere to a consistent color scheme when visualizing results from different brain age estimates within the same plot to facilitate easier visual inspection. Specifically, we use red to represent GM ages, blue for WM age nonrigid, and purple for WM age affine.
Data points from four diagnosis groups are matched regarding age and sex (and time to last CN and time to first MCI for matching CN and CN* data points). The differences between WM age nonrigid and GM age (ours) are adjusted by the mean of the differences for the CN group. Wilcoxon signed-rank tests show significant difference between WM age nonrigid and GM age (ours) on both CN* and AD participants.
The longitudinal data from CN* participants are used for MCI prediction from n years pre-diagnosis in two experimental setups. In the “Global Model” setup, WM age nonrigid shows an advantage from 0 to approximately 3.5 years before MCI. In the “Time-Specific Models” setup, WM age nonrigid shows an advantage up to approximately 4–5 years before MCI. However, these advantages are not statistically significant, as indicated by the overlapping confidence intervals.