December 03, 2020 - Deep learning software can improve medical imaging in hospitals and other care facilities by producingimages in a shorter amount of time, according to a GE Healthcare press release.

At least that is the case for Darryl Sneag, director of peripheral nerve MRI at the Hospital for Special Surgery in New York.

Sneag came to this conclusion after using new software developed by GE Healthcare, which uses a deep learning algorithm to improve MR image reconstruction. 

“What AIR Recon DL has allowed us to do is image sometimes faster, even with a higher spatial resolution, and achieve equal-to-better image quality,” Sneag said in the press release. 

“At the end of the day, it’s helping us to potentially make alternative diagnoses or see anatomical structures much sharper and finer than we might have previously been able to,” he continued. 

Prior to software implementation, patients would have to sit through longer MRI sessions so radiologists could obtain higher signal-to-noise ratio in the final image, GE Healthcare explained. Artificial intelligence in medical imaging can “de-noise” the raw digital data produced during the scan and delivers a clearer signal to the image reconstruction process. 

The system works simultaneously with another technology radiologists at the Hospital for Special Surgery use to pick up signals from the body after being activated by the magnet in the MRI. 

“We’re able to cover an entire arm in one shot through this AIR Coil technology. It’s enabling us to image a much larger region of anatomy within a much shorter period of time, while still maintaining the same image quality,” Sneag said. 

“You can only push the physics so far, or the limitations of the magnet so far. I think we’re just scratching the surface with respect to AIR Recon DL’s capabilities,” he stated. 

During COVID-19, artificial intelligence in medical imaging is helping radiologists and technologists fight the pandemic and keep the number of individuals in hospitals down, lowering the chance of transmission.

An MRI Scanners and IMV Medical Information Division report found that 6.5 million MRI scans have been deferred in the US due to COVID-19. Therefore, a significant effort is needed to process and review images, manage scan times, and disinfect MRI equipment between patients.

Specifically, artificial intelligence not sharpens images in a shorter amount of time, but it can also boost scalable development and provide greater transparency into MRI model design and performance. 

In mid-August, the National Institutes of Health (NIH) launched a medical imaging center that leverages artificial intelligence to fight COVID-19. 

The center, called the Medical Imaging and Data Resource (MIDRC), will create new tools that physicians can use for early detection and personalized therapies for coronavirus patients. 

Essentially, this will help experts predict responses to treatment and improve patient outcomes. 

MIDRC will lead the development and implementation of new diagnostics, such as machine learning algorithms that will “allow rapid and accurate assessment of disease status and help physicians optimize patient treatment.”

Additionally, the center will facilitate rapid and flexible collection and analysis of imaging and associated clinical data, NIH said in the August announcement. Participating organizations will provide expertise within medical imaging, imaging data quality, security, access, and sustainability.

“This major initiative responds to the international imaging community’s expressed unmet need for a secure technological network to enable the development and ethical application of artificial intelligence to make the best medical decisions for COVID-19 patients,” Krishna Kandarpa, MD, PhD, director of research sciences and strategic directions at NIBIB, said in the August announcement. 

“Eventually, the approaches developed could benefit other conditions as well,” Kandarpa concluded.