Saige-Q
DeepHealth, Inc.Saige-Q is a software tool that analyzes digital breast mammograms using artificial intelligence to identify exams that may contain suspicious findings suggestive of breast cancer. It helps radiologists prioritize these exams in their worklist, enabling faster review of potentially concerning cases. The tool provides passive notification codes but does not provide diagnostic decisions and supports both full-field digital mammography and digital breast tomosynthesis images.
Intended Use
Saige-Q is a software workflow tool designed to aid radiologists in prioritizing exams within the standard-of-care image worklist for compatible full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) screening mammograms. It generates a code indicative of suspicion for at least one suspicious finding in the mammogram to support worklist prioritization or triage, intended for passive notification only and not for diagnostic use.
Technology
Saige-Q is a software-only AI device that receives and preprocesses mammogram DICOM files, checks their appropriateness for analysis, analyzes images using deep neural networks trained on cancer-labeled datasets, generates suspicion codes, and returns these outputs to clinical IT systems for radiology worklist integration. It supports both FFDM and DBT mammograms and can be hosted on compatible on-premise servers.
Performance
Performance evaluation included two retrospective multi-center blinded studies on FFDM and DBT mammograms demonstrating high diagnostic accuracy with AUCs of 0.966 and 0.985 respectively. Sensitivity and specificity endpoints exceeded 80% confidence intervals from established breast cancer screening data. Processing times were within clinical expectations: 15.5 seconds median for FFDM and 196.8 seconds for DBT. Subgroup analyses showed consistent performance across lesion type, density, and age.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
11/30/2020
4 months - 2
FDA Approval
4/16/2021
Other devices from DeepHealth, Inc.
- Saige-Dx2024 • 510K
- Saige-Density2022 • 510K
- Saige-Dx2022 • 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.