MRI Contrast Dye Lawsuits: Study Suggests AI Could Reduce Gadolinium Retention Risk

Published on December 11, 2018 by Sandy Liebhard

As patients in the United States continue to file MRI contrast dye lawsuits, a new study suggests artificial intelligence could be used to reduce risks potentially associated with gadolinium retention.

Gadolinium MRI Contrast Dyes

Gadolinium is a toxic heavy metal that enhances the appearance of images on an MRI or MRA scan.

The U.S. Food & Drug Administration (FDA) has approved eight gadolinium-based MRI contrast dyes for use in this country:

• Eovist
• Magnevist
• Multihance
• Omniscan
• OptimMark
• Dotarem
• Gadavist
• Prohance

Until recently, it was thought that the kidneys eliminated gadolinium from the body shortly after the MRI or MRI, so long as a patient had normal renal function.

FDA Gadolinium Retention Warning

Last December, however, the FDA warned that even patients with healthy kidneys may retain gadolinium after an MRI. Apparently, linear agents, including Eovist, Magnevist, Multihance, Omniscan, and OptiMark, are associated with the highest retention risk.

Among other things, the FDA advised doctors to consider the characteristics of each agent when choosing a gadolinium product for patients who may be at higher risk for retention, such as:

• Anyone who will require multiple doses over their lifetime
• Pregnant women
• Children

So far, the FDA has not concluded that retained gadolinium causes any adverse health effects. However, it ordered the manufacturers of gadolinium-based MRI agents to update their product labels to note the potential for retention. In addition, the drug makers must conduct studies to better evaluate the safety and effectiveness of their gadolinium products.

MRI Contrast Dye Lawsuit Allegations

Dozens of people have since filed MRI contrast dye lawsuits for debilitating symptoms and complications allegedly associated with gadolinium retention. Among other things, plaintiffs claim to suffer from a disorder termed “Gadolinium Deposition Disease,” which is purportedly characterized by one or more of the following symptoms:

• Intense burning of the skin and skin substrate
• Intense boring pain in bones or joints
• Brain fog or mental confusion
• Muscle vibrations, pins and needles sensation
• Headache
• Thickening, discoloration, pain in the skin or skin substrate of the distal arms and legs.

Furthermore, plaintiffs in MRI contrast dye lawsuits assert that the drugs’ manufacturers knew for years that gadolinium could be retained in patients with health kidneys, yet did not warn the public about this risk.

Study Used Deep-Learning to Develop Optimized Gadolinium Protocol

This new study was presented last month at the Radiological Society for North America’s 104^th Scientific Assembly and Annual Meeting in Chicago.

“There is concrete evidence that gadolinium deposits in the brain and body,” said study lead author Enhao Gong, Ph.D., researcher at Stanford University in Stanford, California “While the implications of this are unclear, mitigating potential patient risks while maximizing the clinical value of the MRI exams is imperative.”

Dr. Gong and his colleagues collected three MRI images each from a total of 200 patients, including:

• Zero-dose scans, done prior to contrast administration
• Low-dose scans, acquired after 10% of the standard gadolinium dose administration
• Full-dose scans, acquired after 100 percent dose administration

Using deep-learning techniques, the study authors then trained a computer algorithm to create an approximation of the full-dose image by using the zero- and low-dose scan. Neuroradiologists next evaluated the resulting images for contrast enhancement and overall quality.

Algorithm Learned to Create Images Equal to Those from Full-Dose Gadolinium Scans

Apparently, the images that the algorithm created based on the low-dose scans  were equal to those that resulted from a full dose of gadolinium.

“Low-dose gadolinium images yield significant untapped clinically useful information that is accessible now by using deep learning and AI,” Dr. Gong concluded.

In the near future, he and his team will test the algorithm across a broader range of MRI scanners and with different types of contrast agents.

“We’re not trying to replace existing imaging technology,” he said. “We’re trying to improve it and generate more value from the existing information while looking out for the safety of our patients.”