Scientists Develop Model to Make MR Imaging More Reliable, Accurate

MRI, one of the most effective technologies to assess the innermost structures of the human brain, uses a magnetic field and radio waves to produce images of soft tissue. It is non-invasive and does not use radiation, but it has drawbacks.

Participant movement, such as breathing, blinking, or involuntary movements, during an MRI scan can cause blurring and repeated versions of structures, called ghost artifacts. It can be especially difficult for young children to stay still throughout the scan. Since MRI is used to make brain diagnoses and perform neurological research, quality is key.

To help improve the image quality of brain MRI, researchers in the lab of Li Wang, PhD, associate professor of radiology, have created a foundation model that can perform motion correction, super resolution, noise reduction, harmonization, and enhancing imaging contrast. Their research was published in the journal Nature Biomedical Engineering. Yue Sun, a PhD candidate in the Wang lab, was lead author on the paper.

“Imaging quality is important for visualizing brain anatomy and pathology and can help inform clinical decisions,” said Wang, who is also a member of the Biomedical Research Imaging Center. “Our model can perform more accurate and reliable analysis of brain structures, which is critical for early detection, diagnosis, and monitoring of neurological conditions.”

The model, named Brain MRI Enhancement foundation (BME-X), was tested on over 13,000 images from diverse patient populations and scanner types. Researchers found that it outperformed other state-of-the-art methods in correcting body motion, reconstructing high-resolution images from low-resolution images, reducing grainy noise, and handling pathological MRIs.

One of its most notable feats is the model’s ability to “harmonize” images from different MRI scanners. There are various MRI scanners in use across clinics around the country, including those produced by Siemens, GE, and Philips, and each uses different models and imaging parameters. This variability can make it difficult for clinicians and researchers to have clear and consistent results. BME-X can take in all of the data and level the playing field, creating “harmonized” data to be used for clinical or research needs.

Due to its strength in harmonizing data, the newly developed model could also be used to help streamline clinical trials and studies that involve more than one research institution, while developing new, standardized imaging protocols and procedures in the neuroimaging field.