Chest-CAD
Imagen Technologies, IncChest-CAD is a computer-assisted detection software that uses machine learning to analyze adult chest X-rays. It identifies and highlights suspicious regions in various categories like cardiac, lungs, bones, and more, assisting physicians with concurrent reading during diagnosis. This helps improve detection accuracy and clinical workflow efficiency.
Intended Use
Chest-CAD is a computer-assisted detection (CADe) software device that analyzes chest radiograph studies using machine learning techniques to identify, categorize, and highlight suspicious regions of interest (ROI). Any suspicious ROI identified is assigned to one of the following categories: Cardiac, Mediastinum/Hila, Lungs, Pleura, Bones, Soft Tissues, Hardware, or Other. The device is intended as a concurrent reading aid for physicians and is indicated for adults only.
Technology
Chest-CAD uses deep learning algorithms for computer vision to analyze digital chest X-rays, generating DICOM Presentation State overlays highlighting suspicious ROIs categorized into eight classes. It operates on cloud-based platforms and integrates with PACS viewers allowing toggling of annotation overlays.
Performance
Performance testing included standalone validation on 20,000 chest radiographs showing high sensitivity (0.908), specificity (0.887), and AUC (0.976) across all categories. A clinical multi-reader study demonstrated that use of Chest-CAD improved reader accuracy (AUC from 0.836 to 0.894), sensitivity, and specificity in detecting suspicious ROIs compared to unaided reading.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
3/5/2021
4 months - 2
FDA Approval
7/20/2021
Other devices from Imagen Technologies, 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.