VisiRad XR

K223133

Imidex Inc. · cleared 2023-08-03 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“VisiRad XR is a computer aided detection (CADe) software as a medical device (SaMD) product intended to detect lung nodules and masses from 6-60mm in chest radiographs.”

Algorithmmachine learning algorithms

source quote (p.4)

“utilizes machine learning algorithms”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedNo

Validation studies (2)

Retrospective clinical

sample size not stated · 2 site(s)

endpoints: device sensitivity calculated at an image level; Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve

Reader study (MRMC)

n=600 images · 2 site(s)

endpoints: accuracy of readers aided by VisiRad XR as determined by the image-level Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve; sensitivity; specificity

Reported performance (6 observations)

sensitivity0.83CI 0.81-0.84

source quote (p.7)

“Study results demonstrated an overall sensitivity of 0.83 (95% CI: 0.81-0.84) with average false positives per image of 1.5.”

aurocas written: “auc”0.73CI 0.71-0.74

source quote (p.7)

“Overall AUC, calculated non-parametrically, was 0.73 (95% CI: 0.71-0.74).”

false_positive_rate_per_imageas written: “average false positives per image”1.5

source quote (p.7)

“Study results demonstrated an overall sensitivity of 0.83 (95% CI: 0.81-0.84) with average false positives per image of 1.5.”

aurocas written: “average reader improvement in overall average AUC”0.027

source quote (p.8)

“yielding an average reader improvement in overall average AUC for both sites of 0.027.”

sensitivityas written: “average sensitivity increase”0.076

source quote (p.8)

“Average sensitivity across all readers increased by 0.076.”

specificityas written: “average specificity decrease”0.086

source quote (p.8)

“Average specificity across all readers decreased by 0.086”

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).