syngo.CT Lung CAD
Siemens Healthcare GmbHThe syngo.CT Lung CAD by Siemens Healthcare GmbH is a software tool designed to assist radiologists in detecting solid and subsolid lung nodules on chest CT scans. It uses advanced AI algorithms based on convolutional neural networks to highlight suspicious areas, reducing the chance of missed nodules. The software integrates with existing medical imaging platforms, improving clinicians' efficiency and accuracy in lung nodule detection, a critical task in lung cancer screening and diagnosis.
Intended Use
Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid and subsolid pulmonary nodules during review of multi-detector computed tomography (MDCT) of the chest.
Technology
The device uses convolutional neural networks (CNNs) to process isotropic CT volumes: lung segmentation via V-net CNNs, candidate generation with CNN-based filtering, candidate classification by CNNs applying down-sampling convolutions and fully connected layers, and a post-filtering module to reduce false positives from anatomical structures. The software outputs candidate nodules for display by a host application.
Performance
The device underwent a multi-reader multi-case (MRMC) clinical reader study with 20 readers and 232 cases (143 with nodules, 89 without), demonstrating statistically significant improvement in nodule detection sensitivity compared to unaided reading. Non-clinical testing included unit, integration, system tests and validation per recognized standards. Results met all endpoints supporting safety, effectiveness, and substantial equivalence to predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
11/5/2020
4 months - 2
FDA Approval
3/31/2021
Other devices from Siemens Healthcare GmbH
- Syngo Carbon Enterprise Access (VA40A)2024 • 510K
- AI-Rad Companion (Pulmonary)2024 • 510K
- Syngo Carbon Clinicals2023 • 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.