Limbus Contour
K241837Limbus AI Inc. · cleared 2024-10-09 · product code QKB · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.5)
“Limbus Contour is a stand-alone software medical device.”
Algorithmneural network models based on U-Net and ResUNet architectures, trained with Adam optimization algorithm and Sørensen-Dice coefficient loss function
source quote (p.11)
“The architecture for the neural network models used in our device borrows its primary structure from the U-Net (Ronneberger 2015) and ResUNet (Diakogiannisa 2020). We use the Adam optimization algorithm (Kingma 2014) and the Sørensen-Dice coefficient loss function (Sørensen 1948) to train the network.”
Adaptive (vs locked)No
source quote (p.7)
“Locked algorithm; Deep Learning model”
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (1)
Bench
n=10 patients
endpoints: Dice Similarity Coefficient (DSC)
standards: RTOG, RTOG 1106, RTOG 0848, EMBRACE II, DAHANCA, NRG, ESTRO, ACROP, EPTN
Reported performance (5 observations)
diceas written: “Dice Similarity Coefficient (DSC) for A_Aorta”0.909095CI 0.87649337
source quote (p.23)
“A_Aorta 0.909095 0.0455771 10 0.87649337 0.81 Passed”
diceas written: “Dice Similarity Coefficient (DSC) for Bladder”0.96601238CI 0.94024138
source quote (p.23)
“Bladder 0.96601238 0.05220935 21 0.94024138 0.935 Passed”
diceas written: “Dice Similarity Coefficient (DSC) for Brain”0.992205CI 0.99078444
source quote (p.24)
“Brain 0.992205 0.00251205 16 0.99078444 0.988 Passed”
diceas written: “Dice Similarity Coefficient (DSC) for OpticNrv_L”0.82576941CI 0.79173441
source quote (p.28)
“OpticNrv_L 0.82576941 0.06203798 17 0.79173441 0.73 Passed”
diceas written: “Dice Similarity Coefficient (DSC) for Heart”0.95488833CI 0.93656793
source quote (p.26)
“Heart 0.95488833 0.02805647 12 0.93656793 0.89 Passed”
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).