syngo.via MI Workflows; Scenium; syngo MBF

K251528

Siemens Medical Solutions USA, Inc. · cleared 2025-07-03 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
syngo.via MI Workflows (including Scenium and syngo MBF applications) is a multi-modality post-processing software only medical device intended to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The syngo.via MI Workflows applications are part of a larger syngo.via client/server system which is intended to be installed on common IT hardware. The hardware itself is not seen as part of the syngo.via MI Workflows medical device.
Algorithmlung lobe segmentation algorithm; AI/ML segmentation algorithm; PERCIST Liver Reference Region placement algorithm
source quote (p.9)
The lung lobe segmentation algorithm was re-trained with additional data and is utilized within the Auto Lung 3D and Anatomy Segmentation features of the MI General workflow. This AI/ML segmentation algorithm is the same segmentation algorithm as utilized in the Anatomy Segmentation feature of the reference predicate device (K232000). Additionally, performance evaluation was conducted for the updated PERCIST Liver Reference Region placement. The algorithm takes as input the PET/CT image together with a binary liver mask and returns the coordinates of the reference region center.
Adaptive (vs locked)Yes
source quote (p.9)
The lung lobe segmentation algorithm was re-trained with additional data and is utilized within the Auto Lung 3D and Anatomy Segmentation features of the MI General workflow.
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (3)

Retrospective clinical

n=20 patients

endpoints: Dice coefficient (DSC)

Retrospective clinical

n=20 patients

endpoints: Dice coefficient; symmetric surface distance (ASSD)

Retrospective clinical

n=129 patients

endpoints: number of intersections with suspicious uptake masks

Reported performance (2 observations)

diceas written: “average Dice coefficient per organstated without value
source quote (p.10)
The average Dice coefficient for the 20 subjects was higher for each lobe in the subject device than in the predicate device, although not greater than a +0.03 difference for all lobes.
diceas written: “average Dice coefficientstated without value
source quote (p.10)
The acceptance criteria for the liver and all other organs supported by the anatomy segmentation feature is an average Dice coefficient greater than 0.8 or an average symmetric surface distance (ASSD) less than 10 mm. The liver met both criteria.

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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K251528