Intended Use

Assist trained interpreting physicians in analyzing breast ultrasound images of patients with soft tissue breast lesions who are being referred for diagnostic ultrasound. The tool localizes suspicious lesions from two orthogonal views, provides BI-RADS category and descriptors, and may be used to generate structured reports. It is intended as a tool to aid, not replace, physician judgment.

Technology

SMART-B is a web-based machine learning software that processes DICOM breast ultrasound images, localizes soft tissue lesions using AI algorithms, assigns BI-RADS categories and descriptors, and generates structured reports. It accepts images via standard DICOM interfaces, uses automated ROI generation, and allows user modification before report finalization.

Performance

Device performance was validated in both a multi-reader multi-case (MRMC) study (n=589 patients, 16 radiologists) and a standalone study (n=972 unique patients). In the MRMC, use of SMART-B significantly improved reader localization and diagnostic accuracy (increase in LROC AUC from 0.824 to 0.897 with aid, p=0.001). The standalone device achieved an AUCLROC of 0.901, sensitivity of 94.7%, and specificity of 51.4%. Software verification and validation followed FDA and IEC 62304 standards.

Predicate Devices

No predicate devices specified

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.