A global team used deep learning and MRI scans to identify patterns of neuroplasticity in the brains of stroke survivors, which may guide future personalized rehabilitation.
Key Details
- 1Study analyzed MRI scans from over 500 stroke survivors across 34 sites in 8 countries.
- 2Deep learning (graph convolutional networks) estimated brain region biological age from imaging data.
- 3Larger strokes accelerated aging in the damaged hemisphere but paradoxically made the opposite hemisphere appear younger in key motor networks.
- 4AI-detected patterns of regional brain age were linked to the severity of chronic motor impairment.
- 5The ENIGMA Stroke Recovery Working Group harmonized global datasets for the largest neuroimaging analysis of its type.
- 6Findings could help customize patient-specific rehabilitation interventions in the future.
Why It Matters
This research demonstrates the potential of AI-enabled neuroimaging to detect subtle compensatory brain changes post-stroke, offering a pathway to more tailored, effective rehabilitation strategies for stroke recovery. It also highlights the growing role of AI in advancing clinical neuroimaging research.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.