uMI Panvivo (uMI Panvivo); uMI Panvivo (uMI Panvivo S); uMI Panvivo (uMI Panvivo EX); uMI Panvivo (uMI Panvivo ES)

K253564

Shanghai United Imaging Healthcare Co., Ltd. · cleared 2026-02-13 · product code KPS · Radiology

Premarket evidence — what FDA accepted

Device typehardware
source quote (p.6)
“The system is a PET/CT system designed for providing anatomical and functional images.”
AlgorithmDeepMAC is an image post-processing technology that uses pre-trained neural networks to reduce metal artifacts and improve image quality. uExcel DPR (Deep Progressive Reconstruction) is a deep learning-based PET reconstruction algorithm. It utilizes pre-trained deep neural networks on long-axis datasets to optimize the iterative reconstruction process, effectively reducing noise and improving contrast. OncoFocus uses two deep-learning-based AI networks: a body cavity segmentation network (CNN-SEG) for respiratory signal generation, and an attenuation map (u-map) synthesis network (CNN-AC) for more accurate attenuation correction and image registration. NeuroFocus.Brain integrates two deep learning networks: a brain segmentation network (CNN-SEG) for robust motion signal extraction, and a CNN-based attenuation map synthesis network (CNN-AC) for improved u-map estimation and image alignment. AIEFOV algorithm training input and output were derived from system simulations.
source quote (p.14)
“DeepMAC is an image post-processing technology that uses pre-trained neural networks to reduce metal artifacts and improve image quality. The training data is derived from system simulations and contains pairs of image data: on the one hand, images with metal artifacts, and on the other hand, corresponding ground truth images without metal artifacts. The validation datasets of DeepMAC are including the PMMA phantom datasets and clinical dataset from 20 human subjects. uExcel DPR (Deep Progressive Reconstruction) is a deep learning-based PET reconstruction algorithm. It utilizes pre-trained deep neural networks on long-axis datasets to optimize the iterative reconstruction process, effectively reducing noise and improving contrast. There are two deep-learning-based AI networks in OncoFocus, one is the body cavity segmentation network (CNN-SEG) for respiratory signal generation, and the other is the attenuation map (u-map) synthesis network (CNN-AC) for more accurate attenuation correction and image registration. The solution integrates two deep learning networks: a brain segmentation network (CNN-SEG) for robust motion signal extraction, and a CNN-based attenuation map synthesis network (CNN-AC, applicable to FDG only) for improved u-map estimation and image alignment. The input and output for the algorithm training were both derived from system simulations based on the same patient.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.14)
“Content of Premarket Submissions for Management of Cybersecurity in Medical Devices”

Validation studies (5)

Retrospective clinical

n=20 cases

endpoints: average CT value difference in affected area; metal artifact reduction; image quality improvement; tissue interpretability

Retrospective clinical

n=8 cases

endpoints: Contrast recovery (CR); background variability (BV); contrast-to-noise ratio (CNR); noise reduction; SNR improvement; image SNR; diagnostic confidence

standards: NEMA NU 2-2018

Retrospective clinical

n=13 cases

endpoints: Volume relative to no respiratory motion correction (AVolume); Maximal standardized uptake value relative to no respiratory motion correction (ASUVmax); respiratory motion artifacts reduction; PET/CT alignment accuracy; diagnostic confidence

Retrospective clinical

n=7 cases

endpoints: ASUVmean in high-uptake region; quantitative reduction in high-uptake regions caused by head motion correction; head motion artifacts reduction; image quality improvement; diagnostic confidence

Retrospective clinical

n=4 patients

endpoints: accuracy of CT value; accuracy and uniformity of PET image SUV; image Artifacts; homogeneity of same tissue; diagnostic confidence

Reported performance (0 observations)

FDA source did not state a quantitative performance metric — non-reporting is itself the signal.

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

34
recalls in product code, 24mo
8
MAUDE reports in code, 12mo
-72%
vs code's own 3-yr baseline
4
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (GE MEDICAL SYSTEMS ISRAEL, FUNCTIONAL IMAGING 9, Andrey Sakharov Haifa Israel, initiated 2025-12-24): "There is a potential intermittent issue on certain Omni Legend systems that can result in a streaking artifact in the PET clinical scan images. This streaking artifact is most eas" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98269

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (GE MEDICAL SYSTEMS ISRAEL, FUNCTIONAL IMAGING 4, Hayozma St Tirat Carmel Israel, initiated 2025-06-20): "Unintended radial detector motion may occur during patient setup or during patient scan if system does not have correct version of gantry software installed. Unintended detector mo" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97193

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (Hermes Medical Solutions AB Strandbergsgatan 16 Stockholm Sweden, initiated 2024-10-31): "Due a potential software/configuration issue that may result is incorrect alignment during reconstructing a SPECT/CT study." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:95673

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (Canon Medical System, USA, INC., initiated 2024-09-17): "When PET-CT system is executing reconstruction, if PET acquisition for another patient is performed (or PET reconstruction for another patient is performed from raw data processing" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:95471

Recalls attributed to this device

  • Recalling firm matches this device's applicant (Shanghai United Imaging Healthcare Co., Ltd. No. 2258 Chengbei Rd, Jiading Ind. Shanghai China) — same firm and product code, not necessarily this device · initiated 2023-03-01

    Due to a software issue where the process of patient scanning, the scatter correction may occasionally fail with will potentially cause a failure of the PET image reconstruction and generation of PET images.

    recall event 91870 (openFDA)

  • Recalling firm matches this device's applicant (Shanghai United Imaging Healthcare Co., Ltd. No. 2258 Chengbei Rd, Jiading Ind. Shanghai China) — same firm and product code, not necessarily this device · initiated 2022-05-30

    The wireless VSM module of a mobile PET/CT system, operating in an environment with strong Wi-Fi signals, may experience ECG signal and respiratory signal loss due to Wi-Fi interference. ECG and respiratory signal loss during acquisition can result in the failure of ECG and respiratory-gated reconstruction of the PET scan, which may require rescanning of the patient.

    recall event 90888 (openFDA)

  • Recalling firm matches this device's applicant (Shanghai United Imaging Healthcare Co., Ltd. No. 2258 Chengbei Rd, Jiading Ind. Shanghai China) — same firm and product code, not necessarily this device · initiated 2021-08-02

    The EXAM acquisition workflow could occasionally freeze after canceling the PET scan.

    recall event 88521 (openFDA)

  • Recalling firm matches this device's applicant (Shanghai United Imaging Healthcare Co., Ltd. No. 2258 Chengbei Rd, Jiading Ind. Shanghai China) — same firm and product code, not necessarily this device · initiated 2021-08-02

    The EXAM acquisition workflow could occasionally freeze after canceling the PET scan.

    recall event 88521 (openFDA)

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K253564