TAIMedImg DeepMets

K250427

Taiwan Medical Imaging Co., Ltd. · cleared 2025-05-28 · product code QKB · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning.”

Algorithmartificial intelligence algorithm, deep learning neural networks

source quote (p.4)

“TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The AI inference module consists of image preprocessing, deep learning neural networks, and postprocessing components, and is intended to contour brain metastasis on the axial T1-weighted contrast-enhanced (T1WI+C) MR images. It utilizes deep learning neural networks to generate contours and annotations for the diagnosed brain metastases.”

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)

Retrospective clinical

n=1,029 patients

Retrospective clinical

n=158 patients · 16 site(s)

endpoints: Lesion-Wise Sensitivity (Se); False Positive Rate (FPR); Dice Similarity Coefficient (DSC); Hausdorff Distance (HD); Centroid Distance (CD)

standards: IEC 62304:2006/A1:2016, ISO 14971: 2019

Reported performance (2 observations)

sensitivity89.97CI (86.51, 93.43)

source quote (p.11)

“Lesion-Wise Sensitivity (Se) (%) 89.97 (86.51, 93.43)”

diceas written: “Dice Similarity Coefficient (DSC)”0.7CI (0.67, 0.72)

source quote (p.11)

“Dice Similarity Coefficient (DSC) 0.70 (0.67, 0.72)”

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

—

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).