This week saw announcements from modern AI vendors: an improved county-level population health management company and a Recent York University Langone Health subsidiary that aims to apply physics to improve AI-powered imaging technology.
In addition, with formal approval from the U.S. Food and Drug Administration, the modern, first-of-its-kind imaging software can give physicians access to an advanced noise-removal algorithm that improved MRI image quality in a recent neurological study by Microstructure Imaging.
FDA approves RMT for clinical apply
Microstructure Imaging, a Brooklyn, Recent York-based magnetic resonance imaging software company, announced Wednesday that it has received FDA 501 clearance for breakthroughs in its signal-to-noise diffusion and functional magnetic resonance imaging software.
While MRI machines are often deafening for patients, the noise generated by the images is a bigger issue for their overall care. MRI uses a robust magnetic field and radio waves to make detailed images of organs and tissues, but the clarity of the image is governed by the signal-to-noise ratio, a calculation that indicates the difference between the area of interest and the background at each pixel.
While more medical understanding can be gained from higher SNR images, the addition of a random matrix theory algorithm, MICSI claims, provides a “multiplicative increase in SNR.”
The software, called MICSI-RMT, is the first to bring RMT denoising to clinical practice, the company says, making it particularly groundbreaking for neuroimaging applications such as stroke treatment, where precise imaging improves medical decision-making.
The company said in a statement that the software can improve MRI image quality without external training data or powerful graphics processors, unlike customary AI-assisted imaging. statement.
This means the AI-powered approach to noise cancellation doesn’t cause hallucinations, according to the company website.
MICSI-RMT also processes modules that support weighted linear least squares and Bayesian fitting techniques, which facilitate quantitative analysis of diffusion imaging. The company noted that DICOM data routing provides secure integration into medical workflows.
In the company’s blinded rater study, neuroradiologists evaluated MICSI-RMT-processed and standard-of-care MRI images and reported a preference for MICSI-RMT imaging because of its clarity and reduced artifacts. They also said that MICSI-RMT-processed DTI images had sharper visualization of petite structures in the brain’s white matter and better contrast with adjacent tissue types. They also reported more anatomically relevant activation maps with functional MRI images acquired using RMT technology.
The researchers found that RMT technology improved diffusion MRI by 4.35x and fMRI by 1.9x, and offered more precise parametric mapping. There was also a significant improvement – 56.3% – in dMRI enhancement with ADC map precision.
County increases patient analysis
Innovaccer Inc., a healthcare artificial intelligence platform company, announced Wednesday that San Mateo County Health will apply its population health management platform to improve patient care services and manage data on approximately 165,000 people and 500,000 decedents countywide.
By compiling data from SMCH systems and integrating with electronic health records, healthcare providers can search for patients across multiple EHR systems, review long-term patient records and transfer data back to their primary EHR systems, the company said.
“This partnership is a great example of teams successfully working together to seamlessly integrate data and streamline care delivery while bringing back the joy of care,” Abhinav Shashank, co-founder and CEO of Innovaccer, said in a statement.