A new AI model uses MRI scans to generate detailed, region-specific brain aging maps to better characterize normal aging and neurodegeneration.
Key Details
- 1Model developed at the University of Southern California using deep-learning neural networks.
- 2Trained on MRI scans from 14,748 cognitively normal adults (ages 19–100).
- 3Tested on over 1,900 participants, including 1,102 cognitively normal, 354 with mild cognitive impairment, 529 with Alzheimer's disease.
- 4The AI maps revealed advanced aging in brain regions such as the hippocampus and amygdala in patients with early MCI and Alzheimer's.
- 5Local brain age gaps were statistically significant (p < 0.05) and linked to cognitive performance.
- 6Model may aid early detection, monitoring, and tailored clinical trial recruitment, but further validation is needed.
Why It Matters
This approach gives radiologists and researchers more anatomically precise biomarkers for Alzheimer’s and related disorders, potentially enabling earlier and more accurate detection and prognosis. The results highlight the value of AI-powered imaging for personalized brain health monitoring.
Source
AuntMinnie
Related News
•Radiology Business
RSNA Launches Real-World AI Challenge for Knee MRI Interpretation
RSNA introduces its first AI challenge combining knee MRI images and radiology reports to enhance detection and classification of knee abnormalities.
•Radiology Business
AI-Powered Tool Streamlines CT Scan Prioritization in Emergency Departments
An AI-based CT queue system significantly reduces wait times for ED patients by prioritizing scans likely to reveal critical findings.
•Radiology Business
AI Workflow Enables General Radiologists to Match Breast Specialists in Screening
AI-powered workflow helps generalist radiologists detect breast cancer at rates comparable to specialists.