Intended Use

A computer-aided detection (CAD) system intended to identify and mark regions of interest (ROIs) associated with solitary pulmonary nodules on digitized frontal chest radiographs, as an aid after initial radiographic interpretation.

Technology

The device uses an algorithm with multiple features derived from clinical and image data, including multi-resolution analysis and multiple-stage classification processes such as heuristic decision rules, artificial neural networks, and fuzzy logic to detect lung nodules. It processes digitized chest radiographs from a film digitizer and outputs marked images on a video display and printed hard copies.

Performance

Clinical testing included a pivotal study with radiologists interpreting 240 chest radiograph cases containing 80 lung cancer and 160 non-cancer cases. Results showed improved radiologist performance in lung cancer detection when using the RS-2000 as an aid, with increased ROC performance across various nodule sizes, although with some increase in false positives. The device achieved an average device sensitivity of 80% for T1 lung cancer detection in reproducibility testing.

Ready to Sharpen Your Edge?

Subscribe to join 11k+ 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.