The U.S. Food and Drug Administration (FDA) has granted 510(k) clearance for DeepHealth Breast Ultrasound, an AI-powered software solution that automates breast lesion detection, characterization, and reporting. The software is designed to standardize and improve the accuracy and efficiency of breast ultrasound imaging by integrating sonographer and radiologist workflows into a single platform.  

DeepHealth Breast Ultrasound assists in localizing suspicious lesions in breast ultrasound images. In a study submitted to the FDA, the software localized breast lesions with more than 98% accuracy and improved the sensitivity of breast cancer detection by 8%. It also reduced radiologists’ time for American College of Radiology Breast Imaging Reporting and Data System lesion characterization and interpretation by 37%.

DeepHealth is a wholly owned subsidiary of RadNet, Inc., a provider of diagnostic imaging services. RadNet validated the ultrasound software in live clinical settings and in a multireader, multicase study of 16 U.S. board-certified radiologists. The study was submitted to the FDA in support of the 510(k) clearance.  

The FDA clearance allows DeepHealth Breast Ultrasound to be marketed commercially in the United States for patients who can acquire reimbursement. The software joins the company’s breast imaging platform, which includes multiple AI applications for breast cancer detection.  

“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,” said Jason McKellop, MD, Medical Director of Women’s Imaging for RadNet California. “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.” 

“No single imaging pathway addresses every woman’s needs.  With the addition of DeepHealth 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,” said Niccolò Stefani, MD, Business and Product Leader, Clinical AI at DeepHealth. 

ASCO AI in Oncology is published by Conexiant under a license arrangement with the American Society of Clinical Oncology, Inc. (ASCO^®). The ideas and opinions expressed in ASCO AI in Oncology do not necessarily reflect those of Conexiant or ASCO. For more information, see Policies.