Lunit INSIGHT MMG

K211678

Lunit Inc. · cleared 2021-11-17 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.11)
“Software-only device”
Algorithmartificial intelligence algorithm
source quote (p.6)
“The software applies an artificial intelligence algorithm for recognition of suspicious lesions, which are trained with large databases of biopsy proven examples of breast cancer, benign lesions and normal tissues.”
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=2,412 images

endpoints: ROC AUC; LROC AUC; Sensitivity; Specificity

Reader study (MRMC)

n=240 images

endpoints: diagnostic ability of radiologist with CAD assistance; FBR (Forced BI-RADS) ROC AUC; LCM LROC AUC; LCM ROC AUC; recall rate in cancer group (sensitivity); recall rate in non-cancer group (1-specificity)

Reported performance (13 observations)

sensitivity85.74CI 82.95, 88.53
source quote (p.8)
“Sensitivity (%) [95% CI] 85.74 [82.95, 88.53]”
specificity75.62CI 73.64, 77.60
source quote (p.8)
“Specificity (%) [95% CI] 75.62 [73.64, 77.60]”
aurocas written: “auc”0.903CI 0.889-0.917
source quote (p.8)
“ROC AUC [95% CI] 0.903 [0.889, 0.917]”
aurocas written: “Type I LROC AUC”0.781CI 0.751, 0.812
source quote (p.8)
“Type I LROC AUC [95% CI] 0.781 [0.751, 0.812]”
aurocas written: “Type II LROC AUC”0.792CI 0.763, 0.822
source quote (p.8)
“Type II LROC AUC [95% CI] 0.792 [0.763, 0.822]”
aurocas written: “ROC AUC (unaided, reader study)”0.754CI 0.702, 0.807
source quote (p.9)
“ROC AUC (95%CI) 0.754 (0.702, 0.807)”
aurocas written: “ROC AUC (aided, reader study)”0.805CI 0.759, 0.852
source quote (p.9)
“ROC AUC (95%CI) 0.805 (0.759, 0.852)”
aurocas written: “Inter-test difference in ROC AUC (aided - unaided)”0.051CI 0.027-0.075
source quote (p.9)
“For the primary endpoint, the average inter-test difference in ROC AUC between Test 2 and Test 1 was 0.051 (95% CI: 0.027-0.075) with statistical significance (P=0.0001)”
aurocas written: “LCM LROC AUC (inter-test difference)”0.094CI 0.056 - 0.132
source quote (p.9)
“LCM LROC 0.094 (95% CI: 0.056 - 0.132)”
aurocas written: “LCM ROC AUC (inter-test difference)”0.052CI 0.026 - 0.079
source quote (p.9)
“LCM ROC AUC 0.052 (95% CI: 0.026 - 0.079)”
sensitivityas written: “Recall rate in cancer group (sensitivity) (inter-test difference)”5.97CI 2.48 - 9.46
source quote (p.9)
“recall rate in cancer group (sensitivity) 5.97(95% CI: 2.48 - 9.46)”
sensitivityas written: “Recall rate in non-cancer group (1-specificity) (inter-test difference)”-1.46CI -3.41 - 0.05
source quote (p.9)
“recall rate in non-cancer group (1-specificity) -1.46 (95% CI: -3.41 - 0.05)”
aurocas written: “ROC AUC (standalone performance on reader study cases)”0.863CI 0.818 - 0.909
source quote (p.9)
“ROC AUC in the standalone performance analysis is 0.863 (95% CI: 0.818 - 0.909)”

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/K211678