CT VScore+
Canon Medical Informatics, Inc.CT VScore+ is a software tool that helps clinicians evaluate calcified lesions in coronary arteries from non-contrast cardiac CT scans. It automatically calculates calcium scores, highlights calcium deposits on the images, and provides visualization aids to support cardiovascular risk assessment for patients aged 30 and older. The software uses deep learning to segment coronary arteries and quantify calcium, allowing for semi-automated, accurate, and reproducible results to improve clinical interpretation.
Intended Use
CT VScore+ is a software application intended for non-invasive evaluation of calcified lesions of the coronary arteries based on ECG-gated, non-contrast cardiac CT images for patients aged 30 years or older. The device automatically generates calcium scores for the coronary arteries (combined LM+LAD, RCA, LCX) and highlights the segmented calcium on the original CT image. The device also offers the option for the user to display the calcium scores in the context of reference data from the MESA and Hoff-Kondos databases. The segmentation map of calcifications is intended for informational use only and is not intended for detection or diagnostic purposes.
Technology
CT VScore+ incorporates a deep learning algorithm using a proprietary Attention UNet architecture to segment coronary calcifications on ECG-gated, non-contrast cardiac CT DICOM images, automatically generating Agatston and volume calcium scores for combined LM+LAD, RCA, and LCX arteries. It runs on the Vitrea platform and allows user manual edits. The device outputs calcium scores and 3D rendered calcium views for supplementary visualization.
Performance
Performance testing included validation on 236 independent patient cases with deep learning model development on 210 cases. The device demonstrated high agreement with ground truth manual scoring by board-certified physicians, achieving ICC >0.99 for total scores, high kappa scores for risk classification, and robust segmentation accuracy (Dice score ≥0.87 per vessel). Performance was consistent across scanner types (Canon, GE, Siemens, Philips), slice thickness, noise levels, patient demographics, and disease severity. No new safety or effectiveness concerns were identified.
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Subscribe to join 7,100+ 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.