The Food and Drug Administration (FDA) has granted clearance for marketing of an artificial-intelligence assisted image processing software (SublleMR; Subtle Medicine, Menlo Park, CA) that uses denoising and resolution enhancement to improve image quality, including brain MRI.
The artificial intelligence image analysis system delivers a significant improvement in the quality of noisy images, which is particularly beneficial for patients who have difficulty holding still for long periods of time. Artifact-ridden images and the need for rescans are a challenge for patients and physicians. The artificial intelligence image analysis system integrates seamlessly into the radiology workflow and it is compatible with any brand of MRI scanner and PACS.
Subtle Medical's focus is on applying the latest deep learning algorithms to image acquisition, an area of considerable importance in healthcare given the millions of scans conducted at busy radiology departments and imaging centers. "We are pleased to receive FDA clearance for the artificial intelligence image analysis system, and we look forward to helping radiology departments and imaging centers get the most out of their existing MRI scanners," said Enhao Gong, PhD, founder and CEO of Subtle Medical. "This is an important milestone for the company as it broadens our portfolio of technologies developed for radiologists and their patients."
"One of the most exciting things about deep learning reconstruction is how it redefines the usual negotiation between exam time and image quality. This could lead to significant downstream value for imaging operations and for patient experience," said Christopher Hess, MD, Chair of the Department of Radiology and Biomedical Imaging at UCSF.
The artificial intelligence image analysis system utilizes proprietary deep learning algorithms to bring the latest imaging enhancement technology to existing scanners. It is currently in pilot clinical use in multiple university hospitals and imaging centers.
Mitchell S. V. Elkind, MD, MS
Shruti Bhandari, MD; Rohit Kumar, MD; Megan Nelson, MD; Donald Miller, MD; and Brian J. Williams, MD
Peter McAllister, MD