Intended Use

Aid to the reader during screening of 3D breast ultrasound images produced by the somo.v Automated Breast Ultrasound System, to detect mammography-occult lesions in women with dense breast parenchyma.

Technology

Software package consisting of a CAD engine employing image pattern recognition and artificial neural networks to automatically identify suspicious areas in 3D breast ultrasound images, combined with a viewer to display native ABUS images alongside CAD outputs with highlighted suspicious regions.

Performance

Clinical multi-reader multi-case study demonstrated non-inferior breast cancer detection performance with QVCAD aid compared to ABUS alone, and a statistically significant (33%) reduction in interpretation time. Standalone CAD sensitivity was around 71% for CAD marks and 97% for enhanced dark areas, with specificity varying accordingly. Performance was validated on 185 screening cases including 52 cancer cases.

Ready to Sharpen Your Edge?

Subscribe to join 7,600+ 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.