University of Michigan's AI model, Prima, can diagnose brain MRI scans in seconds, achieving up to 97.5% accuracy in identifying neurological conditions.
Key Details
- 1Prima is a vision-language AI model developed for brain MRI diagnostic interpretation.
- 2Tested on over 30,000 MRI studies with up to 97.5% diagnostic accuracy across 50+ neurological disorder classes.
- 3Trained on over 200,000 MRI studies and 5.6 million sequences from U-M Health data.
- 4Outperformed other state-of-the-art models in neurodiagnostic accuracy and urgency prioritization.
- 5Can recommend relevant subspecialty providers to be alerted for urgent cases.
- 6Results published in Nature Biomedical Engineering; initial-stage evaluation.
Why It Matters
Prima demonstrates the potential of scalable, AI-driven neuroimaging interpretation, enabling faster, highly accurate workflows for clinical diagnosis and triage. With radiologist shortages and rising MRI demand globally, such tools could significantly reduce diagnostic delays and improve patient outcomes.
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.