Summary: In a massive international study, researchers have discovered a surprising pattern of neuroplasticity in stroke survivors. Using deep learning to analyze brain scans from over 500 survivors across eight countries, researchers found that while a stroke accelerates aging in the damaged hemisphere, the undamaged side of the brain actually begins to look “younger” in its structure.
This regional rejuvenation—particularly in areas responsible for motor planning and attention—appears to be the brain’s way of “retooling” healthy networks to compensate for severe physical impairment.
Key Facts
- Brain-PAD Marker: Researchers used AI to calculate the “Brain-Predicted Age Difference” (brain-PAD). A “younger” brain age in undamaged regions served as a sensitive marker for neural reorganization.
- The Contralesional Shift: Survivors with the most severe movement deficits showed the most “youthful” structural patterns in the hemisphere opposite their injury, especially within the frontoparietal network.
- Global Collaboration: The study was part of the ENIGMA Stroke Recovery Working Group, harmonizing data from 34 research sites to create the world’s largest dataset of its kind.
- Paradoxical Adaptation: This youthful shift doesn’t necessarily mean the movement has fully recovered; rather, it reflects the brain physically adapting and “rejuvenating” healthy tissue to pick up the slack for the damaged motor system.
Source: USC
In a new study published in The Lancet Digital Health, scientists at the USC Mark and Mary Stevens Neuroimaging and Informatics Institute (Stevens INI) have discovered that the brains of people who experience severe physical impairment after a stroke may reorganize themselves in unexpected ways, showing signs of “younger” brain structure in undamaged regions as they adapt to injury.
The international research effort is part of the Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) Stroke Recovery Working Group, which analyzed brain scans from more than 500 stroke survivors across 34 research sites in eight countries.
Using deep learning models trained on tens of thousands of MRI scans, the researchers estimated the “brain age” of different regions in each hemisphere to see how stroke damage affects brain structure and recovery.
“We found that larger strokes accelerate aging in the damaged hemisphere but paradoxically make the opposite side of the brain appear younger,” said Hosung Kim, PhD, associate professor of research neurology at the Keck School of Medicine of USC and co-senior author of the study.
“This pattern suggests the brain may be reorganizing itself, essentially rejuvenating undamaged networks to compensate for lost function.”
The research team used an advanced form of artificial intelligence known as a graph convolutional network to predict the biological age of 18 brain regions from MRI data. The difference between a person’s predicted brain age and their actual chronological age, known as the brain-predicted age difference (brain-PAD), served as a sensitive marker of neural health.
When the team associated these measurements with motor performance scores, they found a striking pattern: stroke survivors with severe movement deficits, even after more than 6 months of rehabilitation, showed younger-than-expected brain age in regions opposite the lesion, particularly within the frontoparietal network, a key system involved in motor planning, attention, and coordination.
“These findings suggest that when stroke damage leads to greater movement loss, undamaged regions on the opposite side of the brain may adapt to help compensate,” Kim explained.
“We saw this in the contralesional frontoparietal network, which showed a more ‘youthful’ pattern and is known to support motor planning, attention, and coordination. Rather than indicating full recovery of movement, this pattern may reflect the brain’s attempt to adjust when the damaged motor system can no longer function normally. This gives us a new way to see neuroplasticity that traditional imaging could not capture.”
The study was conducted through ENIGMA, a global alliance that unites data from more than 50 countries to better understand the brain across diseases. Researchers harmonized MRI data and clinical measures across dozens of cohorts to build the world’s largest stroke neuroimaging dataset of its kind.
“By pooling data from hundreds of stroke survivors worldwide and applying cutting-edge AI, we can detect subtle patterns of brain reorganization that would be invisible in smaller studies. These findings of regionally differential brain aging in chronic stroke could eventually guide personalized rehabilitation strategies,” said Arthur W. Toga, PhD, director of the Stevens INI and Provost Professor at USC.
The team plans to expand their work to include longitudinal studies tracking patients from the acute to chronic stages of stroke recovery. By observing how patterns of brain aging and reorganization develop over time, clinicians might be able to customize interventions based on each patient’s unique neural adaptation process, ultimately improving recovery outcomes and quality of life in the near future.
Key Questions Answered:
A: It’s not about reversing time, but about structural density and connectivity. The AI models found that in response to a major “clog” or “break” in the motor system, the healthy side of the brain recruits more resources and builds more robust connections, mimicking the flexible, dense structure typically seen in younger brains.
A: Paradoxically, the “youngest” patterns were seen in those with the most severe physical impairments. This suggests that the brain only hits the “emergency rejuvenation” button when the damage is so extensive that the original motor pathways can no longer function at all.
A: Currently, rehab is often “one size fits all.” By using AI to see which parts of a patient’s brain are trying to “rejuvenate,” doctors could eventually create personalized physical therapy that targets and strengthens those specific healthy networks.
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this neurology and stroke research news
Author: Laura LeBlanc
Source: USC
Contact: Laura LeBlanc – USC
Image: The image is credited to Neuroscience News
Original Research: Closed access.
“Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study” by Gilsoon Park, Mahir H. Khan, Justin W. Andrushko, Nerisa Banaj, Michael R. Borich, Lara A. Boyd, Amy Brodtmann, Truman R. Brown, Cathrin M. Buetefisch, Adriana B. Conforto, Steven C. Cramer, Michael Dimyan, Martin Domin, Miranda R. Donnelly, Natalia Egorova-Brumley, Elsa R. Ermer, Wuwei Feng, Fatemeh Geranmayeh, Colleen A. Hanlon, Brenton Hordacre, Neda Jahanshad, Steven A. Kautz, Mohamed Salah Khlif, Jingchun Liu, Martin Lotze, Bradley J. MacIntosh, Feroze B. Mohamed, Jan E. Nordvik, Fabrizio Piras, Kate P. Revill, Andrew D. Robertson, Christian Schranz, Nicolas Schweighofer, Na Jin Seo, Surjo R. Soekadar, Shraddha Srivastava, Bethany P. Tavenner, Gregory T. Thielman, Sophia I. Thomopoulos, Daniela Vecchio, Emilio Werden, Lars T. Westlye, Carolee J. Winstein, George F. Wittenberg, Jennifer K. Ferris, Chunshui Yu, Paul M. Thompson, Sook-Lei Liew, and Hosung Kim. Lancet Digital Health
DOI:10.1016/j.landig.2025.100942
Abstract
Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study
Background
Stroke leads to complex chronic structural and functional brain changes that specifically affect motor outcomes. The brain predicted age difference (PAD) has emerged as a sensitive biomarker of both sensorimotor and cognitive function after stroke. Our previous study showed a higher global brain PAD associated with poorer motor function after stroke.
However, the association between local stroke lesion load, regional brain age, and motor impairment is unclear. This study aimed to investigate the associations between focal lesion damage, regional brain PAD in both hemispheres, and motor outcomes in chronic stroke, and to identify key predictors of motor impairment.
Methods
In this multicohort, retrospective, observational study, we included individuals with chronic unilateral stroke (>180 days post stroke) from the ENIGMA Stroke Recovery Working Group dataset and used individuals from the UK Biobank cohort to train the regional brain age prediction model. Structural T1-weighted MRI scans were used to estimate regional brain PAD in 18 predefined functional subregions via a graph convolutional network algorithm.
Lesion load for each region was calculated on the basis of lesion overlap. Linear mixed-effects models assessed associations between lesion size, local lesion load, and regional brain PAD. Machine learning classifiers predicted motor outcomes using lesion loads and regional brain PADs. Structural equation modelling examined directional relationships among corticospinal tract lesion load, ipsilesional brain PAD, motor outcomes, and contralesional brain PAD.
Findings
We included 501 individuals from the ENIGMA Stroke Recovery Working Group dataset (34 cohorts in eight countries) and 17 791 individuals from the UK Biobank dataset. Larger total lesion size was positively associated with higher ipsilesional regional brain PADs (older brain age) across most regions (β=0·5420 to 0·9458 across significantly correlated regions, false discovery rate [FDR]-corrected p<0·05), and with lower brain PAD in the contralesional ventral attention and language network region (β=–0·3747, 95% CI –0·6961 to –0·0534, FDR-corrected p<0·05).
Higher local lesion loads showed similar patterns. Specifically, lesion load in the salience network significantly influenced regional brain PADs across both hemispheres. Machine learning models identified corticospinal tract lesion load (adjusted mean difference –0·0905, 95% CI –0·1221 to –0·0589, p<0·0001), salience network lesion load (–0·0632, –0·0906 to –0·0358, p<0·0001), and regional brain PAD in the contralesional frontoparietal network (0·9939, 0·4929 to 1·4950, p=0·0001) as the top three predictors of motor outcomes.
Structural equation modelling revealed that higher corticospinal tract lesion load was associated with poorer motor outcomes (β=–0·355, 95% CI –0·446 to –0·267, p<0·0001), which were further linked to younger contralesional brain age (0·204, 0·111 to 0·295, p<0·0001), suggesting that severe motor impairment is linked to compensatory decreases in contralesional brain age.
Interpretation
Our findings reveal that larger stroke lesions are associated with accelerated ageing in the ipsilesional hemisphere and paradoxically decelerated brain ageing in the contralesional hemisphere, suggesting compensatory neural mechanisms. Assessing regional brain age might serve as a biomarker for neuroplasticity and inform targeted interventions to enhance motor recovery after stroke.
Funding
US National Institutes of Health.
