Synapse 3D Base Tools (V7.0)

K243762

FUJIFILM Corporation · cleared 2025-05-21 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“The 3D image analysis software Synapse 3D Base Tools (V7.0) is medical application software running on Windows server/client configuration installed on commercial general-purpose Windows-compatible computers.”

Algorithmdeep learning method called as "Fully Convolutional Network"

source quote (p.10)

“Some new segmentation applications are added and implemented using the same deep learning method called as "Fully Convolutional Network".”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.17)

“The confidentiality, integrity and availability are maintained by Synapse 3D Base Tools in accordance with Section IV (B.) of the Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions (April 8, 2022).”

Validation studies (1)

Retrospective clinical

n=1,086 cases

endpoints: DICE (Average); 95% Hausdorff Distance; Mean Surface Distance

standards: Digital Imaging and Communications in Medicine (DICOM) Set (PS 3.1 – 3.20) (2016), IEC 62304 Edition 1.1 2015-06, Medical Device Software - Software Life Cycle Processes, ISO 14971:2019 2019-12-10, Medical Devices - Application of Risk Management to Medical Devices

Reported performance (5 observations)

diceas written: “DICE (Average) for Duodenum (CT)”0.85

source quote (p.15)

“Duodenum (CT) 30 0.85”

diceas written: “DICE (Average) for Stomach (CT)”0.96

source quote (p.15)

“Stomach (CT) 30 0.96”

diceas written: “DICE (Average) for Pancreas section (Tail) (CT)”0.99

source quote (p.15)

“Pancreas section (Tail) (CT) 29 0.99”

diceas written: “DICE (Average) for Prostate (MRI)”0.9

source quote (p.16)

“Prostate (MRI) 30 0.9”

diceas written: “DICE (Average) for Rectal ROI (tumor) (MRI)*”0.75

source quote (p.16)

“Rectal ROI (tumor) (MRI)* 27 0.75”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

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).