Image: AI-Powered SubtleMR is designed to enhance MRI images (Photo courtesy of Subtle Medical).
Proprietary denoising and resolution augmentation algorithms powered by artificial intelligence (AI) make enhancement technology available to existing magnetic resonance imaging (MRI) scanners.
The Subtle Medical (Menlo Park, CA, USA) SubtleMR software platform can provide significant improvement to the quality of noisy images, and it is compatible with any brand of MRI scanner and picture archiving and communication system (PACS). The software solution integrates seamlessly with the scanner, reducing acquisition time and improving the patient experience during imaging procedures, while boosting exam throughput and provider profitability.
SubtleMR uses algorithms similar to those of the company’s first product, SubtlePET, an AI solution that enables completion of more PET exams compared to conventional PET imaging, without the need for additional capital expenditure, and SubtleGAD, which is designed to reduce gadolinium dosage during imaging procedures. The use of the AI-powered products is particularly beneficial for patients who have difficulty holding still for long periods of time, reducing the proportion of artifact-ridden images and the need for re-scans that provide a challenge for both patients and physicians.
“We look forward to helping radiology departments and imaging centers get the most out of their existing MRI scanners. Our focus on image acquisition and workflow differentiates us from other AI companies that are working on post-processing and computer-aided diagnosis products,” said Enhao Gong, PhD, founder and CEO of Subtle Medical. “We are not replacing radiologists, we are addressing the tremendous cost to U.S. healthcare by leveraging deep learning in imaging at the infrastructure level to enable better and higher quality care.”
“One of the most exciting things about deep learning reconstruction is how it redefines the usual negotiation between exam time and image quality,” said Christopher Hess, MD, chair of the department of radiology and biomedical imaging at the University of California, San Francisco (UCSF; USA). “This could lead to significant downstream value for imaging operations and for patient experience.”