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
Rad Partners Wins $1.29M FDA Grant for AI Radiology Report Evaluation Study
Cognita Imaging, part of Rad Partners, has received a $1.29M FDA grant to develop a new framework using large language models (LLMs) to evaluate AI-generated radiology reports.
•Radiology Business
Real-World Study: Radiology AI Best in Emergency and Inpatient Settings
A commercial AI tool for intracranial aneurysm detection outperformed in inpatient and emergency settings but yielded limited benefits for outpatients in a major health system study.
•Radiology Business
New Rubric Enhances Safety of AI-Generated Radiology Summaries
Researchers developed a five-factor rubric to assess the safety and quality of AI-generated, patient-friendly radiology report summaries.