BoneMetrics (US)

K241593

Gleamer SAS · cleared 2025-02-05 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“BoneMetrics US is a fully automated radiological image processing software device intended to aid users in the measurement of Cobb angles on frontal spine radiographs of individuals of at least 4 years old for patients with suspected or present spinal deformities, such as scoliosis. It should not be used instead of full patient evaluation or solely relied upon to make or confirm a diagnosis. The software device is to be used by healthcare professionals trained in radiology. ... Software application.”

AlgorithmThe device uses machine learning techniques and an AI algorithm, specifically Convolutional neural networks, for classification and landmarking, combined with classical methods for computing angles.

source quote (p.5)

“BoneMetrics US is intended to analyze radiographs using machine learning techniques to provide fully automated measurements of cobb angles during the review of frontal spine radiographs. ... Once received by BoneMetrics US, the radiographs are automatically processed by the AI algorithm without requiring any user inputs. The algorithm identifies the keypoints corresponding to the corners of all the vertebras that are seen on the images and calculates all possible angles between vertebras. ... Convolutional neural networks for: classification, landmarking. Classical methods for computing: angles.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=345 images

endpoints: Mean Absolute Error (°) for Cobb angle with the largest curvature; Mean Absolute Error (°) for Minor Cobb angle

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

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).