Rayvolve LN

K243831

AZmed · cleared 2025-03-26 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“Rayvolve LN is a computer-aided detection software device to assist radiologists to identify and mark regions in relation to suspected pulmonary nodules from 6 to 30mm size.”

Algorithmdeep learning techniques

source quote (p.7)

“It is a standalone software that uses deep learning techniques to detect and localize pulmonary nodules on chest X-rays.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (2)

Standalone

n=2,181 images

Reader study (MRMC)

n=400 cases

endpoints: determine whether the diagnostic accuracy of readers aided by Rayvolve LN was superior to reader accuracy when unaided by Rayvolve LN, as determined by the AUC of the ROC curve; report the sensitivity and specificity per image of Rayvolve LN aided and unaided reads, and the Alternative Free Response Receiver Operating Characteristic (AFROC), False Positives Per Image and sensitivity per nodule of Rayvolve LN aided and unaided reads; Time was evaluated per-user performance and per-specialty performance at image level

Reported performance (9 observations)

sensitivity0.8935CI 0.8836; 0.9027

source quote (p.12)

“Reader sensitivity per image was significantly improved from 0.7975 (95% CI: 0.7848; 0.8097) to 0.8935 (95% CI: 0.8836; 0.9027)”

specificity0.851CI 0.8396; 0.9027

source quote (p.12)

“Reader specificity per image was improved from 0.8235 (95% CI: 0.8114; 0.8350) to 0.8510 (95% CI: 0.8396; 0.9027)”

aurocas written: “auc”0.8583

source quote (p.12)

“Reader AUC improved from 0.8071 to 0.8583 (a difference of 0.0511) (95% CI: 0.0501; 0.0518)”

sensitivityas written: “Standalone Sensitivity”0.8847CI 0.8638; 0.9028

source quote (p.11)

“The results of standalone testing at image level demonstrated that Rayvolve LN detects pulmonary nodules with sensitivity (0.8847, 95% Wilson's Confidence Interval (CI): 0.8638; 0.9028)”

specificityas written: “Standalone Specificity”0.8294CI 0.8066; 0.9028)

source quote (p.11)

“specificity (0.8294; 95% Wilson's CI: 0.8066; 0.9028)”

aurocas written: “Standalone AUC”0.8408CI 0.8272; 0.8548)

source quote (p.11)

“Area Under The Curve (AUC) of the Receiver Operating Characteristic (ROC) (0.8408; 95% Bootstrap CI: 0.8272; 0.8548).”

aurocas written: “Unaided Reader AUC”0.8071

source quote (p.12)

“Reader AUC improved from 0.8071 to 0.8583 (a difference of 0.0511) (95% CI: 0.0501; 0.0518)”

sensitivityas written: “Unaided Reader Sensitivity”0.7975CI 0.7848; 0.8097

source quote (p.12)

“Reader sensitivity per image was significantly improved from 0.7975 (95% CI: 0.7848; 0.8097) to 0.8935 (95% CI: 0.8836; 0.9027)”

specificityas written: “Unaided Reader Specificity”0.8235CI 0.8114; 0.8350

source quote (p.12)

“Reader specificity per image was improved from 0.8235 (95% CI: 0.8114; 0.8350) to 0.8510 (95% CI: 0.8396; 0.9027)”

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).