uMR Jupiter

K250246

Shanghai United Imaging Healthcare Co., Ltd. · cleared 2025-08-05 · product code LNH · Radiology

Premarket evidence — what FDA accepted

Device typehardware
source quote (p.4)
“The uMR Jupiter system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces sagittal, transverse, coronal, and oblique cross sectional images, and spectroscopic images, and that display internal anatomical structure and/or function of the head, body and extremities.”
Algorithmhybrid water-fat separation algorithm (WFI) utilizing deep learning and an artificial intelligence (AI) network for accurate initialization; temporal AI-assisted Compressed Sensing (t-ACS) dynamic MR imaging technique utilizing deep learning priors; deep-learning based image processing algorithm (DeepRecon) for intelligent image de-noising and K-space-interpolation based image super-resolution; deep learning algorithms (EasyScan) for automatic slice group placement; function (EasyFACT) for automatic ROI placement and numerical statistics on liver; function (EasyCrop) for automatic cropping of MRA images
source quote (p.13)
“The WFI (Water-Fat Imaging) is a hybrid water-fat separation algorithm, which utilizes deep learning to improve the stability of conventional algorithms. The framework of WFI is based on the conventional Regional Iterative Phasor Extraction (RIPE) algorithm. Although RIPE has already been widely used for water fat separation in clinical setting, this method is sensitive to phasor initialization and thus subject to water-fat swap artifacts. To overcome this challenge, an artificial intelligence (AI) network has been trained to provide a more accurate initialization for the RIPE algorithm. (page 13) t-ACS (temporal AI-assisted Compressed Sensing) is a dynamic magnetic resonance (MR) imaging technique, which utilizes the low-rank characteristics of time dimension, physical model and deep learning priors. t-ACS technique reconstructs multi-phase MR data and outputs multi-phase images. (page 14) DeepRecon is a deep-learning based image processing algorithm for intelligent image de-noising and K-space-interpolation based image super-resolution. (page 17) EasyFACT workflow, based on the FACT sequence, automatically places the ROI (Regions of Interest) of 5 suitable locations on the liver and performs numerical statistics of quantitative values (FF and R2*), including mean, maximum, minimum and other information, and outputs online reporting. (page 18) EasyScan is a workflow feature that automatically locates slice groups. This function is based on deep learning algorithms, which identify, locate or segment specific tissue structures in images, and calculate the position and orientation of slice groups to achieve automatic placement of slice groups. (page 19) EasyCrop is a function that enables automatic cropping of images scanned with the MRA images to simplify the workflow, after enabling the EasyCrop function, the original images of MRA images will still be saved.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedYes
source quote (p.12)
“Content of Premarket Submissions for Management of Cybersecurity in Medical Devices”

Validation studies (8)

Bench

sample size not stated

standards: ANSI/AAMIES60601-1: 2005/ (R) 2012+A1:2012+C1:2009/(R)2012+A2:2010/(R)2012) [IncludingAmendment2(2021)], IEC 60601-1-2:2014+A1:200, IEC 60601-2-33 Ed. 4.0:2022, IEC 60825-1: 2014, Edition 3.0, IEC 60601-1-6:2010+A1:2013+A2:2020, Edition 3.2, IEC 62304:2006+AMD1:2015 CSV Consolidated version, IEC 62464-1 Edition 2.0: 2018-12, NEMA MS 1-2008(R2020), NEMA MS 2-2008(R2020), NEMA MS 3-2008(R2020), NEMA MS 4-2023, NEMA MS 5-2018, NEMA MS 6-2008(R2014, R2020), NEMA MS 8-2016, NEMA MS 9-2008(R2020), NEMA MS 14-2019, IEC/TR 60601-4-2: 2024, NEMA PS 3.1-3.20(2022d), Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, Content of Premarket Submissions for Management of Cybersecurity in Medical Devices, ISO 10993-5: 2009, Edition 3.0, ISO 10993-10: 2021, Edition 4.0, ISO 10993-23: 2021, Edition 1.0, Use of International Standard ISO 10993-1, ISO 14971: 2019, Edition 3.0, Code of Federal Regulations, Title 21, Part 820, Code of Federal Regulations, Title 21, Subchapter J

Retrospective clinical

n=144 cases

endpoints: clinical diagnosis requirements

Bench

sample size not stated

endpoints: MAE; PSNR; SSIM; local structure measurement (distance); motion-time curves; Bland-Altman analysis

Retrospective clinical

n=35 patients

endpoints: MAE; PSNR; SSIM; local structure measurement (distance); motion-time curves; Bland-Altman analysis

Retrospective clinical

n=2,216 cases

endpoints: clinical diagnosis requirements; diagnosis quality scores

Retrospective clinical

n=5 patients

endpoints: effectiveness of the algorithm (subjective evaluation)

Retrospective clinical

n=40 cases

endpoints: pass criteria (99.3%); safety and effectiveness

Retrospective clinical

n=5 patients

endpoints: pass criteria (100%); safety and effectiveness

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

100
recalls in product code, 24mo
510
MAUDE reports in code, 12mo
+5%
vs code's own 3-yr baseline
3
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K252371 (decision 2025-09-25) from Shanghai United Imaging Healthcare Co., Ltd. for a matching device line ("uMR 680") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K252371

  • recall_reason_pattern

    Software/algorithm-related recall in product code LNH (Philips North America, initiated 2026-04-14): "The potential for stiffness value errors when a specific range of image reconstruction parameters is used in combination with Resoundant's algorithm, leading to the reconstruction " Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98779

  • recall_reason_pattern

    Software/algorithm-related recall in product code LNH (Philips North America, initiated 2025-12-03): "The potential for stiffness value errors when viewing exported MR Elastography (MRE) stiffness maps to viewer Picture Archiving and Communication System (PACS)." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98111

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/K250246