Artificial Intelligence May Help Reduce Gadolinium Dose in MRI Patients


CHICAGO, Nov. 26 / PRNewswire / – Researchers are using artificial intelligence to reduce the dose of a contrast agent that can be left behind in the body following MRI scans, according to a study being presented today at the annual meeting of the Radiological Society of North America (RSNA).

Gadolinium is a heavy metal used in contrast material that improves magnetic resonance imaging. Recent studies have found that traces of the metal remain in the bodies of people who have had tests with certain types of gadolinium. The effects of this deposition are not known, but radiologists are working proactively to optimize patient safety while preserving the important information that gadolinium-enhanced magnetic resonance imaging (MRI) provides.

The story continues below

Ad Statistics

Heading: 9717
Times viewed: 44

Questions to Ask and Considerations about Magnetic Resonance Coil Repair Processes

What to expect from MRI coil repairs that meet clinical expectations and boost ROI. Click to get a standards guideline to wait and require repairs on sustainable magnetic resonance coils

"There is concrete evidence that gadolinium deposits in the brain and body," said lead author of the study, Enhao Gong, Ph.D., a researcher at Stanford University in Stanford, California. "Although the implications of this are unclear, mitigating potential risks to the patient to maximize the clinical value of MRIs is imperative."

Dr. Gong and his colleagues at Stanford have been studying deep learning as a way to achieve this goal. Deep learning is a sophisticated artificial intelligence technique that teaches computers by example. Through the use of models called convolutional neural networks, the computer can not only recognize images but also find subtle distinctions between image data that a human observer may not be able to discern.

To train the deep learning algorithm, the researchers used magnetic resonance imaging of 200 patients who received magnetic resonance imaging with contrast for a variety of indications. They collected three sets of images for each patient: pre-contrast scans, done before contrast administration and referred to as zero dose scans; low dose sweeps, acquired after 10% of the administration of the standard gadolinium dose; and full dose sweeps, obtained after 100 percent dose administration.

The algorithm learned to approximate full-dose examinations of zero dose and low dose imaging. Neuroradiologists evaluated the images to improve contrast and overall quality.

The results showed that the image quality was not significantly different between the low dose MRI images improved by the algorithm and the full-dose and full-contrast MRI images. Initial results also demonstrated the potential to create the equivalent of full-dose contrast MR images without any use of contrast agent.


Source link