Getting a brain MRI can be a nerve-wracking experience, mostly because of the wait. After the scan, it usually takes days to hear back from a doctor. However, researchers at the University of Michigan have developed a new AI model, called Prima, that can read these scans and offer a diagnosis in just a few seconds.
In a recent study published in Nature Biomedical Engineering, the team found that Prima was up to 97.5% accurate. Additionally, it figured out which patients needed help the fastest.
“As the global demand for MRI rises and places significant strain our physicians and health systems, our AI model has potential to reduce burden by improving diagnosis and treatment with fast, accurate information,” said Dr. Todd Hollon, a neurosurgeon at U-M Health.
Faster MRI Results
Most medical AI is trained to do one specific thing, like looking for a single type of tumor. Prima is different. The team trained it on every MRI taken at the University of Michigan since they started using digital records decades ago, that’s over 200,000 studies.
Explore Tomorrow's World From Your Inbox
Get the latest science, technology, and sustainability content delivered to your inbox.
I understand that by providing my email address, I agree to receive emails from Tomorrow's World Today. I understand that I may opt out of receiving such communications at any time.
The system also looks at a patient’s medical history to understand why the scan was ordered in the first place. This helps it act less like a basic calculator and more like a specialist.
“Prima works like a radiologist by integrating information regarding the patient’s medical history and imaging data to produce a comprehensive understanding of their health,” explained Samir Harake, a data scientist at the university. “This enables better performance across a broad range of prediction tasks.”
A Co-Pilot For Doctors
When the AI spots something urgent, like a stroke or a brain bleed, it can instantly alert the right specialist.
“Accuracy is paramount when reading a brain MRI, but quick turnaround times are critical for timely diagnosis and improved outcomes,” said Yiwei Lyu, a postdoctoral fellow at U-M. “At key steps in the process, our results show how Prima can improve workflows and streamline clinical care without abandoning accuracy.”
The team hopes to eventually use this technology for other scans, like X-rays and ultrasounds. Dr. Hollon said, “Prima aims to be a co-pilot for interpreting medical imaging studies.”
