[ad_1]
CHICAGO, Nov. 26, 2018 / PRNewswire / – Researchers use artificial intelligence to reduce the dose of a contrast agent likely to be left in the body after MRI scans, according to a study Presented today at the annual meeting of the North American Radiology Society (RSNA).
Gadolinium is a heavy metal used as a contrast medium to enhance MRI images. Recent studies have shown that traces of the metal remain in the bodies of people who have undergone examinations with certain types of gadolinium. The effects of this repository are not known, but radiologists work proactively to optimize patient safety while preserving the important information provided by gadolinium MRI scans.
The story continues under the advertisement
Ad Stats
Number of hours displayed: 545013
Number of times visited:
THE LEADER OF MEDICAL IMAGING TECHNOLOGY SINCE 1982. REPAIR SALES-SERVICES
Special offers available on displays, patient monitors, recorders, printers, racks, ultrasound devices and cameras for medical use.This includes major brands such as SONY, BARCO, NDS, NEC, LG, EDAN, EIZO, ELO, FSN , PANASONIC, MITSUBISHI, OLYMPUS, AND LARGE.
"There is concrete evidence of the presence of gadolinium deposits in the brain and body," said lead author of the study, Enhao Gong, Ph.D., a researcher at Stanford University's Stanford, California. "The implications of this phenomenon are unclear, mitigating the potential risks to the patient maximizing the clinical value of MRI scans is imperative."
Dr. Gong and his Stanford colleagues are studying deep learning as a way to achieve this goal. In-depth learning is a sophisticated technique of artificial intelligence that teaches computer examples. Through the use of models called convolutional neural networks, the computer can not only recognize images, but also identify subtle distinctions between imaging data that a human observer might not have. not be able to discern.
To train the deep learning algorithm, the researchers used MRI images of 200 patients who underwent contrast enhanced MRI scans for various indications. They collected three sets of images for each patient: pre-contrast analyzes performed before contrast administration and called zero-dose analyzes; low-dose scans, acquired after 10% of the standard dose of gadolinium administered; and full-dose assays, acquired after 100% administration.
The algorithm has learned to approximate full-dose scans from zero-dose, low-dose images. Neuroradiologists then evaluated the images for contrast enhancement and overall quality.
The results showed that the image quality was not significantly different between low-dose, algorithm-optimized MRI images and full-dose, contrast-enhanced IR images. The first results also demonstrated the possibility of creating the equivalent of full-dose, contrast-enhanced MRI images without the use of contrast agent.
[ad_2]
Source link
