Saige-Dx
DeepHealth, Inc.Saige-Dx is an AI-based software that analyzes digital breast tomosynthesis mammograms to detect suspicious soft tissue lesions and calcifications that may indicate cancer. It provides radiologists with a suspicion level for each finding and the entire case, helping improve detection accuracy and reduce reading time during breast cancer screening.
Intended Use
Saige-Dx analyzes digital breast tomosynthesis (DBT) mammograms to identify the presence or absence of soft tissue lesions and calcifications that may be indicative of cancer. Outputs are for use as a concurrent reading aid for interpreting physicians on screening mammograms with compatible DBT hardware.
Technology
Saige-Dx is AI software processing screening mammograms using DICOM formats from DBT studies, analyzing both DBT image stacks and 2D images. It detects findings, assigns suspicion levels per finding and case, and produces DICOM Structured Reports and Secondary Capture objects for viewing and summary reporting.
Performance
Performance was validated in retrospective, multi-center studies including a multi-reader study with 18 MQSA-qualified radiologists and a standalone study with 1304 cases. With Saige-Dx, reader AUC improved from 0.865 to 0.925, sensitivity increased by 8.8%, and specificity slightly improved. Saige-Dx standalone AUC was 0.930. Diverse patient populations and various breast densities and lesion types were included.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
1/12/2022
4 months - 2
FDA Approval
5/12/2022
Other devices from DeepHealth, Inc.
- Saige-Dx2024 • 510K
- Saige-Density2022 • 510K
- Saige-Q2021 • 510K
Ready to Sharpen Your Edge?
Join hundreds of your 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.