Aorta-CAD

K213353

Imagen Technologies, Inc · cleared 2022-09-20 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“Aorta-CAD is computer-assisted detection (CADe) software device that analyzes chest radiograph studies for suspicious regions of interest (ROIs).”

AlgorithmThe device uses a deep learning algorithm to identify ROIs and produce boxes around the ROIs. Aorta-CAD uses modern deep learning and computer vision techniques to analyze chest radiographs. Supervised Deep Learning

source quote (p.5)

“The device uses a deep learning algorithm to identify ROIs and produce boxes around the ROIs. Aorta-CAD uses modern deep learning and computer vision techniques to analyze chest radiographs.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.7)

“HIPAA Compliant”

Validation studies (2)

Standalone

n=5,000 cases

endpoints: sensitivity; specificity; Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve

Reader study (MRMC)

n=244 cases

endpoints: accuracy of readers aided by Aorta-CAD superior to unaided readers per category as determined by the case-level Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve

Reported performance (7 observations)

sensitivity0.91CI 95% Wilson's Confidence Interval: 0.896, 0.922

source quote (p.8)

“The results of the standalone testing demonstrated that Aorta-CAD detects ROIs with high sensitivity (0.910; 95% Wilson's Confidence Interval: 0.896, 0.922)”

specificity0.896CI 95% Wilson's Confidence Interval: 0.889, 0.902

source quote (p.8)

“high specificity (0.896; 95% Wilson's Confidence Interval: 0.889, 0.902)”

aurocas written: “auc”0.974CI 95% Bootstrap Confidence Interval: 0.971, 0.977

source quote (p.8)

“high Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve (0.974, 95% Bootstrap Confidence Interval: 0.971, 0.977).”

ppvas written: “Positive Predictive Value (Aortic calcification suggestive of Aortic Atherosclerosis)”0.812CI (0.794, 0.829)

source quote (p.10)

“Positive Predictive Value 0.812 (0.794, 0.829)”

npvas written: “Negative Predictive Value (Aortic calcification suggestive of Aortic Atherosclerosis)”0.958CI (0.951, 0.965)

source quote (p.10)

“Negative Predictive Value 0.958 (0.951, 0.965)”

ppvas written: “Positive Predictive Value (Dilated aorta suggestive of Aortic Ectasia)”0.296CI (0.263, 0.331)

source quote (p.10)

“Positive Predictive Value 0.296 (0.263, 0.331)”

npvas written: “Negative Predictive Value (Dilated aorta suggestive of Aortic Ectasia)”0.99CI (0.987, 0.993)

source quote (p.10)

“Negative Predictive Value 0.990 (0.987, 0.993)”

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

-100%

vs code's own 3-yr baseline

drift signals on this device

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).