Median LCS (internal name) / eyonis LCS (trade name) (1.0)

K251474

Median Technologies · cleared 2026-02-06 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.10)
“eyonis® LCS is a software-only device, aka Software as a Medical Device (SaMD).”
AlgorithmAI/ML technology-based end-to-end CADe/CADx Software; proprietary AI and Machine Learning models; deep learning modules
source quote (p.5)
“eyonis® LCS is an Al/ML technology-based end-to-end CADe/CADx Software as Medical Device (SaMD) intended to allow early detection, localization and characterization of pulmonary parenchymal nodules from LDCT DICOM images produced during Chest CT examinations. ... These algorithms employ proprietary Al and Machine Learning models trained with large databases containing proven examples of lung cancer lesions and benign nodules. ... A chain of medical image processing and machine learning techniques are implemented. The device includes 'deep learning' modules for recognition of suspicious lesions. These modules are trained with very large databases of cancer and normal patients proven by biopsy or follow-up.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedYes
source quote (p.9)
“Postmarket Management of Cybersecurity in Medical Devices ... Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions ... Cybersecurity in Medical Devices: Refuse to Accept Policy for Cyber Devices and Related Systems Under Section 524B of the FD&C Act”

Validation studies (2)

Retrospective clinical

n=1,147 patients · 7 site(s)

endpoints: patient-level AUROC; sensitivity at COT; specificity at COT; AULROC

Reader study (MRMC)

n=480 images

endpoints: image-level Area Under the Curve (AUC); Sensitivity; Specificity; Increase of inter-reader agreement per patient score; Increase of inter-reader agreement per patient management

Reported performance (12 observations)

sensitivity84.5CI [80.22-88.17]
source quote (p.10)
“a sensitivity at COT of 84.50% [80.22-88.17] p<0.0001 (acceptance criterion: sensitivity at COT > 70%)”
specificity80.25CI [77.33-82.95]
source quote (p.10)
“a specificity at COT of 80.25% [77.33-82.95] p<0.0001 (acceptance criterion: specificity at COT > 70%)”
aurocas written: “auc”0.904CI [0.881-0.926]
source quote (p.10)
“a patient-level AUROC of 0.904 [0.881-0.926] p<0.0001 (acceptance criterion: AUROC>0.800)”
aurocas written: “AULROC”0.869CI [0.843-0.894]
source quote (p.10)
“an AULROC of 0.869 [0.843-0.894] p<0.0001 (acceptance criterion: AULROC>0.750) which confirms eyonis® LCS' localization capability.”
false_positive_rate_per_imageas written: “false-positive rate per scan”0.271CI [0.235-0.313]
source quote (p.10)
“As part of exploratory analyses, FROC analysis yielded a sensitivity at COT of 80.59% [76.20-84.49] and a false-positive rate of 0.271 [0.235-0.313] per scan.”
aurocas written: “aided AUC (reader study)”0.8434
source quote (p.11)
“Results: aided AUC = 0.8434 / unaided AUC = 0.8276 / ΔΑUC (aided – unaided) = 0.0158 [0.0032-0.0288], p = 0.0277.”
aurocas written: “unaided AUC (reader study)”0.8276
source quote (p.11)
“Results: aided AUC = 0.8434 / unaided AUC = 0.8276 / ΔΑUC (aided – unaided) = 0.0158 [0.0032-0.0288], p = 0.0277.”
agreement_kappaas written: “ICC Reader aided (reader study)”0.83CI [0.800-0.856]
source quote (p.11)
“Increase of inter-reader agreement per patient score: ICC Reader aided = 0.830 [0.800-0.856] / ICC Reader unaided = 0.707 [0.659-0.749] / p<0.0001”
agreement_kappaas written: “ICC Reader unaided (reader study)”0.707CI [0.659-0.749]
source quote (p.11)
“Increase of inter-reader agreement per patient score: ICC Reader aided = 0.830 [0.800-0.856] / ICC Reader unaided = 0.707 [0.659-0.749] / p<0.0001”
agreement_kappaas written: “Kappa value reader aided (reader study)”0.4898CI [0.4527-0.5270]
source quote (p.11)
“Increase of inter-reader agreement per patient management: Kappa value reader aided = 0.4898 [0.4527-0.5270] / Kappa value reader unaided = 0.3507 [0.3147-0.3867] / p<0.05”
agreement_kappaas written: “Kappa value reader unaided (reader study)”0.3507CI [0.3147-0.3867]
source quote (p.11)
“Increase of inter-reader agreement per patient management: Kappa value reader aided = 0.4898 [0.4527-0.5270] / Kappa value reader unaided = 0.3507 [0.3147-0.3867] / p<0.05”
aurocas written: “Sub-analysis on US patients: ∆AUC (reader study)”0.017CI [0.006-0.028]
source quote (p.11)
“Sub-analysis on US patients: ∆AUC = 0.017 [0.006-0.028], p<0.05”

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

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K251474