Koios DS for Breast
Koios Medical, Inc.Koios DS for Breast is a machine learning-based software that assists physicians in analyzing ultrasound images of breast lesions. It helps classify breast lesions into BI-RADS categories to support diagnostic accuracy, improve consistency between readers, and provide useful visual confidence indicators. The software processes selected regions of interest on ultrasound images and provides diagnostic support to clinicians.
Intended Use
Koios Decision Support (DS) for Breast is a software application designed to assist trained interpreting physicians in analyzing breast ultrasound images of patients with soft tissue breast lesions, referred for further diagnostic ultrasound examination. It automatically classifies user-selected lesion regions into four BI-RADS-aligned categories (Benign, Probably Benign, Suspicious, Probably Malignant) and classifies lesion shape and orientation.
Technology
Koios DS for Breast is a web-based ASP.NET application that processes user-selected regions of interest from breast ultrasound DICOM images via a machine learning algorithm. It analyzes imaging features referencing a large validated database, producing BI-RADS-aligned categorical outputs along with shape and orientation classifications in under 2 seconds, accessible from any DICOM compliant device.
Performance
Clinical testing involved 15 physicians reading 900 patient cases, showing an increase in diagnostic accuracy (AUC improvement of 0.037) and a significant reduction in inter- and intra-operator variability. Bench testing showed an AUC of 88.2% for malignancy classification and statistical equivalence of shape and orientation classifications compared to expert radiologists.
Predicate Devices
No predicate devices specified
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.