AI could reduce gadolinium dose in MRI
26 Nov 2018 by hdpqmpdbhq.d hdpqmpdbhq.d
AI is being used to reduce the dose of a contrast agent that is often left in the body after an magnetic resonance imaging (MRI) exam.
A team at Stanford University in California studied deep learning to mitigate the potential ricks of gadolinium, a heavy metal used in contrast material for MRI.
Researchers trained a deep learning algorithm with MR images from 200 patients who had had contrast-enhanced MRI exams.
They collected three sets of images for each patient: Zero-dose scans, collected prior to gadolinium administration; low-dose scans, collected after 10 percent of the standard dose; and full-dose scans.
Results showed that the image quality was not significantly different between low-dose, algorithm-enhanced MR images and the full-dose contrast-enhanced MR images.
Dr Enhao Gong, study lead and PhD researcher at Stanford University, said: “Low dose gadolinium images yield significant untapped clinically useful information that is accessible now by using deep learning and AI.
“There is concrete evidence that gadolinium deposits in the brain and body. While the implications of this are unclear, mitigating potential patient risks while maximising the clinical value of the MRI exams is imperative.”
Studies have found traces to remain in the bodies of people who have undergone exams with certain types of gadolinium. Initial results suggest the model’s potential for dramatically reducing gadolinium dose without sacrificing diagnostic quality. Future research will include different types of contrast agent and a broader range of MRI scanners used with the algorithm.
The study is being presented on Monday at the annual meeting of the Radiological Society of North America.
[caption id="attachment_69173" align="alignnone" width="620"]
Credit: Radiological Society of North America[/caption]
