Wednesday, September 23, 2020
Home Lead Story AI Generated Rapid MRI Scans Can be Accurate: Study

AI Generated Rapid MRI Scans Can be Accurate: Study

AI can speed up MRI scans, shows Facebook study

Rapid MRI scans generated with Artificial Intelligence (AI) can be just as accurate, useful and reliable as traditional magnetic resonance imaging, shows a study by Facebook AI researchers and NYU Langone Health.

For the study, radiologists reviewed two sets of knee MRIs from 108 patients — one set using the standard imaging techniques and the other set using the fast MRI AI model.

The results, published in the American Journal of Roentgenology, found no significant differences in the radiologists’ evaluations.

Follow NewsGram on LinkedIn to know what’s happening around the world.

NYU Langone Health and Facebook teamed up to launch the fast MRI initiative two years ago in a bid to speed up MRI scans.

AI can speed up MRI scans, shows Facebook study
The fastMRI scans require four times less data, patients can be imaged much faster and spend less time in the scanning machine, said the study. Pexels

Because the fastMRI scans require four times less data, patients can be imaged much faster and spend less time in the scanning machine, said the study.

“This is an important step toward the clinical acceptance, and utilization of AI-accelerated MRI scans,” Michael Recht, Professor and Chair of Radiology at NYU Langone Health, said in a statement.

To create the image that your clinician or radiologist reviews, the MRI machine uses magnetic fields that interact with hydrogen atoms in the body’s soft tissue and vital organs.

Those atoms then emit electromagnetic signals that act like beacons, indicating where in the body the atoms are located.

The signals are collected by the scanner as a sequence of individual 2D frequency measurements, known as k-space data.

Once all the data is finally collected, the system then applies a complex mathematical formula — an inverse Fourier transform — to that raw k-space data to create detailed MR images of the knee, back, or brain, or other area of the body.

Without a complete set of data points, the math cannot pinpoint exactly where every signal comes from.

The fastMRI team used an entirely different way to create an image — one that requires far less raw data.

The researchers built a neural network and trained it using the world’s largest open source data set of knee MRIs, which was created and shared by NYU Langone Health and as part of the fastMRI initiative.

AI can speed up MRI scans, shows Facebook study
The model then learned to generate complete images from the limited data. Unsplash

The fastMRI research team removed roughly three-fourths of the raw data in each scan and then fed the remaining info into the AI model.

The model then learned to generate complete images from the limited data.

Also Read: Planning For a Baby? Have Some Financial Planning Before!

Importantly, the images produced by the AI model did not just look like generic MRIs; the AI-generated images matched the ground truth image created by the standard slow MRI process, Facebook said.

The study showed that fastMRI can generate “diagnostically interchangeable” MRI images of knee injuries while using about 75 per cent less raw data from the scanning machine.

While the study focused specifically on knee scans, the researchers are now working to extend the results to other parts of the body, such as the brain. (IANS)

STAY CONNECTED

19,144FansLike
362FollowersFollow
1,774FollowersFollow

Most Popular

From “Confusion” To “Clarity” Regarding Sanatan Dharma With Dr. Chandra Shekhar Mayanil

Dr. Chandra Shekhar Mayanil is a Neuroscientist who is currently living in Naperville, Illinois. He has constantly been engaging in topics related to Yog...

Top 5 Beach Activities in Asia

Blessed with some of the most beautiful beaches in the world, Asia has something for everyone. From idyllic white-sand beaches fringed by palm trees...

Here’s Why You Should Switch to Contact Lenses, and It’s Not Just About Looks

Traditionally, we use eyeglasses for correcting vision problems such as near-sightedness (myopia) and far-sightedness (hyperopia). Glasses are both affordable and convenient to wear for...

This Indian Couple Run Street-Side Classes For Poor And Needy Children

On a quiet road in India's capital, tucked away on a wide, red-bricked sidewalk, children set adrift by the country's COVID-19 lockdown are being...

Lockdown Taught Me Greatest Lessons of Life: Mouni Roy

Actress Mouni Roy, who will soon be seen in the digital film, London Confidential, opposite Purab Kohli, says that lockdown taught her some of...

“It is Important To Support Folk Artists and Daily Workers in Trying Times”, Says Popular Singer Shaan

Popular playback singer Shaan says that folk artists and daily workers are keeping the music heritage and industry intact, and it's crucial for the...

Here’s How The Art of “Writing” Became an Empowerment Tool For These Female Authors

By Siddhi Jain Being a female author can come with its own set of challenges, especially when one is trying to juggle a career in...

Self-Driving Cars To Navigate Rush Hour Traffic On This Planet: NASA

A laser-based technology designed to help spacecraft land on a proverbial dime for missions to the Moon and Mars is also helping self-driving cars...

Recent Comments