This browser is not actively supported anymore. For the best passle experience, we strongly recommend you upgrade your browser.
Welcome to Reed Smith's viewpoints — timely commentary from our lawyers on topics relevant to your business and wider industry. Browse to see the latest news and subscribe to receive updates on topics that matter to you, directly to your mailbox.
| 1 minute read

Speeding up the time to perform MRI scans with AI-assisted technology

Magnetic resonance imaging (MRI) is a powerful and effective diagnostic tool, but it can be time consuming, as well as anxiety provoking for some patients. The average MRI exam can take anywhere from 20-40 minutes. In the typical MRI procedure, these scanners produce hundreds, and sometimes thousands, of images. It can take the MRI several minutes to acquire these slices. Those of you who have had MRI scans know that the patient is required to remain still despite being surrounded by loud knocking noises of the magnets. Any movement can extend the time of the scan.

What if MRI scanning time could be reduced? It appears that when machine learning is used to reconstruct MRI images, albeit at a faster pace and with less imaging data acquisition than traditional MRI scans, AI-assisted reconstructions can produce MRI images that are comparable in quality to conventional MRI, according to research just published in the journal Radiology. 

In that research study, AI-assisted MRI image reconstructions of accelerated knee MRI enabled an almost twofold scan time reduction and improved image quality with diagnostic quality equivalent to regular MRI imaging. The radiologists in the study found the AI-reconstructed images to be as good as conventional images for detecting tears or abnormalities, and they found the overall image quality of the accelerated scans to be actually better than some conventional images. 

It is inspiring to read how AI/machine learning can be harnessed to reduce MRI scan time while also offering the added benefit of producing reconstructed MRI images of high diagnostic quality. We are only at the forefront of use of this technology. Will the promise of this research have widespread application across MRI imaging of other anatomical regions? We will want to watch this closely.

In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol.


diagnostic radiology, mri, health care & life sciences