Lunit INSIGHT DBT (V1.2)

K253796

Lunit, Inc. · cleared 2026-03-26 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
Lunit INSIGHT DBT is a computer-assisted detection/diagnosis (CADe/x) Software as a Medical Device that provides information about the presence, location and characteristics of lesions suspicious for breast cancer to assist interpreting physicians in making diagnostic decisions when reading digital breast tomosynthesis (DBT) images.
Algorithmartificial intelligence technology that has been trained via deep learning
source quote (p.6)
The software automatically analyzes digital breast tomosynthesis slices via artificial intelligence technology that has been trained via deep learning.
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=3,277 cases

endpoints: demonstrate that the lower bound of 95% CI of device’s ROC AUC in standalone performance was greater than 0.903 and p-value was less than the significance level of 5% (0.05); JAFROC AUC; Sensitivity at the default operating point (0.1); specificity; Sensitivity at the supplementary ‘0.3’ operating point; specificity at the supplementary ‘0.3’ operating point; Sensitivity at the supplementary ‘0.6’ point; specificity at the supplementary ‘0.6’ point; lesion type agreement analysis

standards: IEC 62304: 2006/A1: 2016, IEC 62366-1:2015+AMD1:2020

Reader study (MRMC)

n=258 cases

endpoints: AI standalone AUROC compared with the average radiologist using the Obuchowski–Rockette (OR) method; AI standalone sensitivity at the highest threshold (Score 60); AI standalone specificity at this threshold

Reported performance (9 observations)

sensitivity91.11CI 89.66, 92.57
source quote (p.9)
Sensitivity at the default operating point (0.1) was 91.11% (95% CI: 89.66, 92.57) and specificity was 77.62% (95% CI: 75.70, 79.54), respectively.
specificity77.62CI 75.70, 79.54
source quote (p.9)
Sensitivity at the default operating point (0.1) was 91.11% (95% CI: 89.66, 92.57) and specificity was 77.62% (95% CI: 75.70, 79.54), respectively.
aurocas written: “auc0.9388CI 0.9304, 0.9472
source quote (p.9)
ROC AUC in the standalone performance analysis was 0.9388 (95% CI: 0.9304, 0.9472) with statistical significance (p < 0.05).
aurocas written: “JAFROC AUC0.9206CI 0.9117, 0.9295
source quote (p.9)
For the secondary endpoints, the result of the JAFROC AUC was 0.9206 (95% CI: 0.9117, 0.9295).
sensitivityas written: “Sensitivity at the supplementary '0.3' operating point88.38CI 86.74, 90.02
source quote (p.9)
Sensitivity at the supplementary ‘0.3’ operating point was 88.38% (95% CI: 86.74, 90.02) and specificity was 83.68% (95% CI: 81.98, 85.38), respectively.
specificityas written: “Specificity at the supplementary '0.3' operating point83.68CI 81.98, 85.38
source quote (p.9)
Sensitivity at the supplementary ‘0.3’ operating point was 88.38% (95% CI: 86.74, 90.02) and specificity was 83.68% (95% CI: 81.98, 85.38), respectively.
sensitivityas written: “Sensitivity at the supplementary '0.6' operating point81.48CI 79.49, 83.47
source quote (p.9)
Sensitivity at the supplementary ‘0.6’ point was 81.48% (95% CI: 79.49, 83.47) and specificity was 93.44% (95% CI: 92.30, 94.58), respectively.
specificityas written: “Specificity at the supplementary '0.6' operating point93.44CI 92.30, 94.58
source quote (p.9)
Sensitivity at the supplementary ‘0.6’ point was 81.48% (95% CI: 79.49, 83.47) and specificity was 93.44% (95% CI: 92.30, 94.58), respectively.
agreement_kappaas written: “matching proportion of the agreement between CAD and ground truther in 3-way classification of lesion type agreement75.61CI 73.40, 77.80
source quote (p.9)
For lesion type agreement analysis, the matching proportion of the agreement between CAD and ground truther in 3-way classification of lesion type agreement was 75.61% (95% CI: 73.40, 77.80).

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). 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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K253796