Medical Image Post-processing Software (uOmnispace.CT)

K242624

Shanghai United Imaging Healthcare Co., Ltd. · cleared 2025-05-14 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“Medical Image Post-processing Software (uOmnispace.CT)”

Algorithmdeep-learning algorithm

source quote (p.7)

“Introduce deep-learning algorithm in applications of Lung Density Analysis, Vessel Analysis, Heart, Liver Evaluation and Cardiovascular Combined Analysis.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.22)

“Cybersecurity Documents”

Validation studies (5)

Retrospective clinical

n=100 patients

endpoints: Dice coefficient

standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2023e), 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)

Retrospective clinical

n=156 patients

endpoints: Dice coefficient

standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2023e), 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)

Retrospective clinical

n=72 patients

endpoints: Dice coefficient

standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2023e), 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)

Retrospective clinical

n=74 patients

endpoints: Dice coefficient

standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2023e), 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)

Retrospective clinical

n=80 patients

endpoints: Dice coefficient

standards: NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2023e), 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)

Reported performance (10 observations)

diceas written: “lung segmentation Dice Similarity Coefficient”0.9801

source quote (p.24)

“lung segmentation 0.9801”

diceas written: “airway segmentation Dice Similarity Coefficient”0.8954

source quote (p.24)

“airway segmentation 0.8954”

diceas written: “Bone removal (Abdomen & Limbs) Dice Similarity Coefficient”0.96957

source quote (p.25)

“Bone removal (Abdomen & Limbs) 0.96957”

diceas written: “Bone removal (Head & Neck) Dice Similarity Coefficient”0.955

source quote (p.25)

“Bone removal (Head & Neck) 0.955”

diceas written: “Coronary artery extraction Dice Similarity Coefficient”0.916

source quote (p.27)

“Coronary artery extraction 0.916”

diceas written: “Heart chamber segmentation Dice Similarity Coefficient”0.97

source quote (p.27)

“Heart chamber segmentation 0.970”

diceas written: “Liver segmentation Dice Similarity Coefficient”0.981

source quote (p.29)

“Liver segmentation 0.981”

diceas written: “Hepatic artery segmentation Dice Similarity Coefficient”0.927

source quote (p.29)

“Hepatic artery segmentation 0.927”

diceas written: “Hepatic portal vein segmentation Dice Similarity Coefficient”0.933

source quote (p.30)

“Hepatic portal vein segmentation 0.933”

diceas written: “Hepatic vein segmentation Dice Similarity Coefficient”0.914

source quote (p.30)

“Hepatic vein segmentation 0.914”

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).