syngo.CT Lung CAD is an AI-powered software tool that helps radiologists detect solid pulmonary nodules in chest CT scans. Acting as a second reader, it alerts clinicians to potential nodules that might have been overlooked during their initial review, thereby improving diagnostic accuracy and patient care.
The syngo.CT Lung CAD device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest that may have been initially overlooked. It is intended to be used as a second reader after the radiologist has completed the initial read.
The device uses deep learning technology based on convolutional neural networks (CNNs) for preprocessing and candidate generation, feature calculation, and classification of pulmonary nodules. It processes images acquired with Siemens multi-detector CT scanners, applying advanced AI algorithms to improve detection accuracy and reduce false positives. Candidate lung segmentation is performed using a CNN-based V-net, and classification is done via a softmax function assigning probabilities for nodules vs. false positives.
The device underwent comprehensive non-clinical verification and validation testing, including unit, integration, system tests, and system validation, showing that the standalone detection sensitivity is superior to the predicate device and the false positive rate is reduced. Results demonstrated safety, effectiveness, and substantial equivalence with improved accuracy over the previous technology.
No predicate devices specified
Submission
11/21/2019
FDA Approval
3/9/2020
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.