Saige-Dx
DeepHealth, Inc.Saige-Dx is an AI-powered software designed to analyze digital breast tomosynthesis mammograms to assist radiologists by detecting soft tissue lesions and calcifications indicative of cancer. It processes DBT image stacks and associated 2D images, outputs suspicious findings with suspicion levels, and helps improve the accuracy and efficiency of breast cancer screening interpretation.
Intended Use
Saige-Dx analyzes digital breast tomosynthesis mammograms to identify the presence or absence of soft tissue lesions and calcifications that may be indicative of cancer, and provides suspicion levels for detected findings and the entire case as a concurrent reading aid for interpreting physicians.
Technology
Saige-Dx is AI-based software that processes DBT image stacks and associated 2D mammography images. It detects findings by outputting bounding boxes and assigns suspicion levels to individual findings and case-level assessment. It encapsulates results into DICOM Structured Reports and Secondary Capture objects for integration with PACS or worklist systems.
Performance
The device was validated through retrospective, blinded multicenter standalone performance testing on 2,002 DBT screening mammograms from 12 US sites with diverse populations, confirming non-inferiority to the predicate device. Testing used independent datasets not overlapping with training data, and included subgroup analyses by breast density, age, ethnicity, and lesion types.
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.