Lung-CAD

K223811

Imagen Technologies, Inc · cleared 2023-09-13 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“Lung-CAD is a computer-assisted detection (CADe) software device that analyzes chest radiograph studies for interstitial thickening.”

Algorithmdeep learning algorithm

source quote (p.3)

“The device uses a deep learning algorithm to identify regions of interest (ROIs) with interstitial thickening and produces boxes around the ROIs.”

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)

standards: FDA's Guidance for Industry and FDA Staff, “Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."

Reader study (MRMC)

n=244 cases

endpoints: accuracy of readers aided by Lung-CAD superior to unaided readers as determined by case-level Area Under the Curve (AUC)

Reported performance (6 observations)

sensitivity0.913CI 0.850, 0.951

source quote (p.8)

“Lung-CAD detects ROIs with high sensitivity (0.913; 95% Wilson's Confidence Interval: 0.850, 0.951)”

specificity0.866CI 0.856, 0.875

source quote (p.8)

“high specificity (0.866; 95% Wilson's Confidence Interval: 0.856, 0.875)”

aurocas written: “auc”0.961CI 0.948, 0.972

source quote (p.8)

“high Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve (0.961, 95% Bootstrap Confidence Interval: 0.948, 0.972)”

ppvas written: “Positive Predictive Value”0.15CI 0.126, 0.177

source quote (p.9)

“Positive Predictive Value 0.150 (0.126, 0.177)”

npvas written: “Negative Predictive Value”0.997CI 0.995, 0.999

source quote (p.9)

“Negative Predictive Value 0.997 (0.995, 0.999)”

aurocas written: “Reader AUC improvement for interstitial thickening”0.0797CI 0.0797, 0.0798

source quote (p.10)

“Reader AUC improvement for interstitial thickening was 0.0797 (95% Confidence Interval: 0.0797, 0.0798).”

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

re_clearance
The FDA AI/ML device list shows a newer 510(k) K230085 (decision 2023-10-03) from Imagen Technologies, Inc for a matching device line ("Lung-CAD") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K230085

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).