RadNet’s DeepHealth Wins FDA Nod for AI-Powered Breast Ultrasound

DeepHealth, a subsidiary of RadNet, has gained U.S. Food and Drug Administration (FDA) 510(k) clearance for DeepHealth Breast Ultrasound, an AI-powered solutions for breast ultrasound imaging.

The technology automates lesion detection, characterization, and reporting to streamline sonographer and radiologist workflows in one experience. The FDA nod adds to DeepHealth’s AI-powered mammography solutions to create a comprehensive breast platform.

Following a multi-reader, multi-case study involving 16 U.S. board-certified radiologists and validation in live clinical settings, DeepHealth Breast Ultrasound is now commercially available in the United States. Customers can pursue reimbursement under an existing Category III CPT code for quantitative ultrasound tissue characterization. RadNet plans to deploy the solution across its network by year-end, where over 700,000 annual breast ultrasound studies may be eligible for reimbursement.

Automated lesion detection helps localize the presence or absence of suspicious soft-tissue lesions in standard breast ultrasound images. It’s shown more than 98% accuracy in localizing lesions and improved sensitivity for breast cancer detection by 8%, according to the company. Images acquired by the sonographer are analyzed to help generate and characterize the lesion shape, orientation, margin, echo pattern, and posterior features, in line with ACR BI-RADS.

The tool generates a radiology report of key findings and impressions to help move more efficiently from image review to final report, while keeping control of the final assessment. It also automatically extracts and organizes lesion measurements, characteristics, and other relevant findings in a standardized format.

Earlier this year, RadNet expanded its mammography partnership with GE HealthCare. The partnership aims to further the innovation, commercialization, and adoption of advanced AI-powered mammography tools.

Comments from RadNet and DeepHealth

Dr. Jason McKellop, Medical Director of Women’s Imaging, RadNet California: “Breast ultrasound is an essential component of the breast care pathway, with approximately 40% of women undergoing the exam at some point in their lives. It is a highly complex, operator-dependent examination, which can lead to significant variability in image acquisition, interpretation and reporting. With DeepHealth’s breast ultrasound solution, we can achieve greater standardization of workflows, improving consistency while saving time for patients, sonographers and radiologists. By streamlining the examination process, we can help reduce exam times, enhance efficiency and ultimately improve patient outcomes.”

Niccolò Stefani, M.D., business and product leader, Clinical AI, DeepHealth: “No single imaging pathway addresses every woman’s needs. With the addition of Breast Ultrasound, we are proud to support women across a broader range of screening and diagnostic pathways, including those with dense breasts and others who may require supplemental imaging. Bringing together AI-powered capabilities across mammography and ultrasound helps clinicians respond to different imaging needs and deliver more comprehensive, personalized breast care.”