This week has seen new vendor announcements for an array of artificial intelligence use cases: enhanced population health management on the county level and a New York University Langone Health spin-off focused on leveraging physics to improve artificial intelligence-powered imaging technology.

Also, with official clearance from the U.S. Food and Drug Administration, new first-of-its-kind imaging software can give clinicians access to a powerful denoising algorithm that improved magnetic resonance imaging quality in a recent neurological study by developer Microstructure Imaging. 

FDA clears RMT for clinical practice

Microstructure Imaging, a Brooklyn, New York-based vendor specializing in MRI software development, announced Wednesday that it had received FDA 501 clearance for its breakthrough in signal-to-noise diffusion and functional MRI software.

While MRI machines are often loud for patients, the noise presented by the images is a greater concern for their overall care. MRI uses a strong magnetic field and radio waves to take detailed images of organs and tissues, but image clarity is subject to an SNR ratio, which is a calculation that indicates the difference between the area of interest and the background at each pixel. 

While more can be understood medically from images with higher SNRs, the addition of a random matrix theory algorithm MICSI said that it has leveraged, provides "a multiplicative boost in SNR."

Called MICSI-RMT, the software is the first to bring RMT denoising into clinical practice, the company said, making it particularly transformative for neuroimaging applications, such as in stroke management, where precise imaging improves medical decision-making.

The software can improve MRI image quality without external training data or high-performance GPUs, unlike traditional AI-enhanced imaging, the company said in a statement.

That means the AI-enhanced denoising approach does not hallucinate, according to the company's website.

MICSI-RMT also processes modules that support weighted linear least squares and Bayesian fitting techniques to facilitate quantitative analysis of diffusion-weighted imaging and noted that DICOM data routing ensures secure integration into medical workflows.

In the company's blinded rater study, neuroradiologists assessed MRI images processed by MICSI-RMT and standard-of-care tools and said they preferred RMT imaging for its clarity and reduced artifacts. They also said DTI images processed with MICSI-RMT had sharper visualization of small structures in brain white matter and improved contrast with adjacent tissue types. They also reported more anatomically appropriate activation maps with functional MRI images produced with RMT technology.

Researchers found the RMT technology improved diffusion MRI 4.35x and fMRI 1.9x and offered more precise parametric mapping. There was also notable improvement – 56.3% – in dMRI enhancement with the precision of ADC maps.

County boosts patient analytics

Innovaccer Inc., a healthcare AI platform company, announced Wednesday that San Mateo County Health will use its population health management platform to improve patient care services and manage data for approximately 165,000 lives and 500,000 legacy lives across the county.

By compiling data across SMCH systems, and integrating into electronic health records, healthcare providers can search for patients across multiple EHR systems, review longitudinal patient records and transition data back to their main EHRs, the company said.

"This partnership is a prime example of teams successfully working together to integrate data seamlessly and improve care delivery, all while bringing back the joy of care," Abhinav Shashank, cofounder and CEO of Innovaccer, said in a statement.

The HIMSS AI in Healthcare Forum is scheduled to take place September 5-6 in Boston. Learn more and register.

Andrea Fox is senior editor of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.