cvi42 Software Application

K242781

Circle Cardiovascular Imaging Inc. · cleared 2024-10-15 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.7)

“cvi42 Software Application (“cvi42”) is a software as a medical device (SaMD) that is intended for evaluating CT and MR images of the cardiovascular system.”

Algorithmmachine learning techniques

source quote (p.7)

“cvi42 uses machine learning techniques to aid in semi-automatic contouring of regions of interest in cardiac MR or CT images.”

Adaptive (vs locked)No

source quote (p.7)

“The separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets. As such, different scans from the same study were not split between the training and validation datasets. None of the cases used for model validation were used for training the machine learning models.”

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Bench

sample size not stated

endpoints: tracking performance; deformation field; performance of the constrained tissue tracking algorithm compared to manual tracking in ES phase by three expert readers; computation of the deformation metrics

standards: ISO 13485:2016, BS EN 62304:2006, ISO 14971:2019, DICOM standards

Retrospective clinical

n=235 patients

endpoints: classification accuracy defined by true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN); Mean volume prediction error (Mean Absolute Error, or MAE); centerline quality and performance (based on TP and FN); success rate for relevant masks

Retrospective clinical

sample size not stated · 9 site(s)

endpoints: performance of the ML-based segmentation of Left Ventricle (LV) cavity, LV myocardium, and Right Ventricle (RV) cavity; mean volume prediction error (Mean Absolute Error in predicted volumetric measures, or MAE); 3D Hausdorff Distance (HD); Dice coefficient

Reported performance (3 observations)

diceas written: “LV cavity segmentation: Dice coefficient”stated without valueCI above 86%

source quote (p.19)

“a Dice coefficient above 86%”

diceas written: “RV cavity segmentation: Dice coefficient”stated without valueCI above 85%

source quote (p.19)

“a Dice coefficient above 85%”

diceas written: “LV myocardium segmentation: Dice coefficient”stated without valueCI above 82%

source quote (p.19)

“a Dice coefficient above 82%”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K251027 (decision 2025-10-27) from Circle Cardiovascular Imaging, Inc. for a matching device line ("cvi42 Coronary Plaque Software Application") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K251027

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).