Logo
RadAI Slice
Subscribe

Intended Use

Intended for use as a non-invasive post-processing software to evaluate calcified plaques in the coronary arteries, which present a risk for coronary artery disease. Analyzes routine non-gated, non-contrast CT studies including entire heart of adults aged 30-85. Generates exact calcium score and a four-category output representing calcium quantity with preview axial images for informational purposes, integrated in radiologist workflow.

Technology

Software device using AI algorithm to automatically detect and estimate coronary artery calcium from non-cardiac-gated adult CT scans. Works with non-gated, non-contrast CT images sent from storage platforms, validates image data, performs deep learning-based heart segmentation and calcium detection, and outputs calcium detection scores and annotated images for review. Operates in conjunction with standard clinical workflow and intended for clinician use as non-diagnostic adjunct.

Performance

Validated on 436 anonymized non-gated CT scans representing diverse acquisition parameters from multiple healthcare institutions. Demonstrated 97.94% yield and overall 89.46% agreement with expert radiologist ground truth calcium category annotations with confidence intervals exceeding acceptance criteria. Correlation of calcium scores with ground truth was high (r=0.959, p<0.0001). Performance compared favorably to radiologists and across imaging characteristics. Demonstrated equivalence to predicate device K210085 with statistically robust clinical validation.

View FDA documentation

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    5/21/2024

    3 months
  • 2

    FDA Approval

    8/19/2024

Other devices from Nano-X AI Ltd.

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.