SpineAR SNAP (SyncAR Spine)

K252054

Surgical Theater, Inc. · cleared 2025-09-29 · product code SBF · Neurology

FDA 510(k) summary for SpineAR SNAP (SyncAR Spine) (K252054)

Constat organizes this clearance into predicate context, validation evidence, reported performance, postmarket signals, and reimbursement links. Each extracted claim stays tied to the public FDA source; missing fields remain explicitly unstated.

Validation studies
2
Cited predicates
1
Performance observations
4
Product code
SBF
Official FDA 510(k) database record ↗FDA 510(k) source PDF ↗

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“The SpineAR SNAP does not require any custom hardware and is a software-based device that runs on a high-performance desktop PC assembled using “commercial off-the-shelf” components that meet minimum performance requirements.SpineAR Software Version SPR.2.0.0 incorporates AI/ML-enabled vertebra segmentation into the clinical workflow to optimize the preparation of a spine surgical plan for screw placement and decompression.”
Algorithm3D U-Net, a type of neural network architecture that excels at medical image segmentation. The algorithm processes the scan iteratively, patch by patch, from the bottom upwards. A key feature is its use of a "memory" channel. As each vertebra is segmented, it is added to this memory channel. This informs the model of what has already been found, preventing it from re-segmenting the same vertebra and guiding it to the next one in the sequence. This iterative approach allows the model to accurately segment every vertebra separately, using a single, robust process.
source quote (p.10)
“The core of the system is a 3D U-Net, a type of neural network architecture that excels at medical image segmentation. The algorithm processes the scan iteratively, patch by patch, from the bottom upwards. A key feature is its use of a "memory" channel. As each vertebra is segmented, it is added to this memory channel. This informs the model of what has already been found, preventing it from re-segmenting the same vertebra and guiding it to the next one in the sequence. This iterative approach allows the model to accurately segment every vertebra separately, using a single, robust process.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedYes
source quote (p.13)
“Cybersecurity testing was conducted and and documentation was provided as recommended in FDA's guidance document “Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions."”

Validation studies (2)

Retrospective clinical

n=95 scans

endpoints: Mean Dice Coefficient (MDC); CT Labeling Accuracy

Retrospective clinical

n=31 scans

endpoints: Mean Dice Coefficient (MDC)

Reported performance (4 observations)

diceas written: “Mean Dice Coefficient (MDC) for Individual vertebrae”0.912CI 0.907
source quote (p.12)
“Individual vertebrae 1193 0.912 0.907”
diceas written: “Mean Dice Coefficient (MDC) for S”0.879CI 0.835
source quote (p.12)
“S 38 0.879 0.835”
diceas written: “Mean Dice Coefficient (MDC) for Sacrum (excl. S1)”0.901CI 0.861
source quote (p.12)
“Sacrum (excl. S1) 38 0.901 0.861”
diceas written: “Mean Dice Coefficient (MDC) for MRI scans”0.903CI 0.891
source quote (p.12)
“208 0.903 0.891”

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

2
recalls in product code, 24mo
4
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
1
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code SBF (Kico Knee Innovation Company, initiated 2025-09-19): "Complaint identified issue with AI surgical planning software that may result in implant malalignment and/or decrease range of motion." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97618

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 2026-09-02.

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 Neurology 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.

Related FDA clearances

More AI/ML devices under product code SBF

These are recent clearances in the same FDA product-code category. Shared classification does not by itself make a device an appropriate predicate.

xvision Spine system

K251639

Augmedics, Ltd.

cleared 2025-10-03

xvision Spine system

K250255

Augmedics Ltd.

cleared 2025-03-13

ARVIS® Shoulder

K243950

Kico Knee Innovation Company Pty Ltd

cleared 2025-01-13

xvision Spine System

K241481

Augmedics Ltd.

cleared 2024-10-16

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K252054