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. It assigns Suspicion Levels for each detected finding and for the entire case and is used as a concurrent reading aid for interpreting physicians on screening mammograms with compatible DBT hardware.

Technology

Saige-Dx is a software-only AI device that processes DICOM files from DBT mammography exams, analyzing both 3D image stacks and 2D images. It applies machine learning algorithms to detect suspicious findings, generating bounding boxes and suspicion levels at the finding and case level, outputting results in DICOM Structured Report and Secondary Capture formats for integration with PACS and workstation displays.

Performance

Performance testing included standalone validation on an independent dataset of 1,804 screening DBT exams from multiple clinical sites and diverse populations. The study demonstrated non-inferior and comparable accuracy to the predicate device across multiple vendors and imaging conditions, with a case-level AUC of 0.910. Additional testing confirmed safety and effectiveness on exams with Hologic HD images, unilateral breasts, and breast implants. Software verification testing showed compliance with requirements and no unintended differences from predicate.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    6/18/2024

    5 months
  • 2

    FDA Approval

    11/18/2024

Other devices from DeepHealth, Inc

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.