uAI Portal
K240411Shanghai United Imaging Intelligence Co., Ltd. · cleared 2024-09-06 · product code QIH · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“uAI Portal is a software solution intended to be used for viewing, manipulation, communication, and storage of medical images.”
AlgorithmArtificial intelligence algorithms for automatic segmentation results.
source quote (p.8)
“uAI Portal offers a fast and user-friendly solution for reconstructing medical images by utilizing automatic segmentation results generated by artificial intelligence algorithms.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.24)
“• Cybersecurity Documents”
Validation studies (1)
Retrospective clinical
n=150 images
endpoints: Dice coefficient
standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set, ISO 14971 Medical devices – Application of risk management to medical devices (Third Edition 2019-12), IEC 62304 Medical device software - Software life cycle processes (Edition 1.1 2015-06 CONSOLIDATED VERSION)
Reported performance (9 observations)
diceas written: “Dice coefficient (Coronary Artery - Vessels segmentation)”0.92
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Coronary Artery Vessels segmentation 0.920”
diceas written: “Dice coefficient (Coronary Artery - Heart segmentation)”0.98
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Coronary Artery Heart segmentation 0.980”
diceas written: “Dice coefficient (Head and Neck Vessel - Head vessel segmentation)”0.902
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Head and Neck Vessel Head vessel segmentation 0.902”
diceas written: “Dice coefficient (Head and Neck Vessel - Neck vessel segmentation)”0.967
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Head and Neck Vessel Neck vessel segmentation 0.967”
diceas written: “Dice coefficient (Aorta - Trunk segmentation)”0.946
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Aorta Trunk segmentation 0.946”
diceas written: “Dice coefficient (Aorta - Branches segmentation)”0.846
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Aorta Branches segmentation 0.846”
diceas written: “Dice coefficient (Pulmonary Artery - Arteries segmentation)”0.953
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Pulmonary Artery Arteries segmentation 0.953”
diceas written: “Dice coefficient (Pulmonary Artery - Veins segmentation)”0.933
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Pulmonary Artery Veins segmentation 0.933”
diceas written: “Dice coefficient (Lower Extremity Artery - Arteries segmentation)”0.892
source quote (p.26)
“The results output by algorithm were compared with the reference standard, the value of Dice coefficient were shown in the table below: Application Algorithm Average Dice Lower Extremity Artery Arteries segmentation 0.892”
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
3
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).