FDA-cleared profile

BoneView

Gleamer

BoneView 1.1-US analyzes eligible 2D radiographs as a concurrent fracture-reading aid. Limb examinations apply to patients aged 2 years and older; pelvis, hip, femur, ribs, thoracic spine, and lumbosacral spine are limited to adults older than 21 years. Clinical users retain diagnostic and patient-management responsibility.

MSK and bone

Evidence status: each field shows source quality, applicability, and review date. Research pending, information not established in reviewed sources, and vendor documentation pending are distinct outcomes.

Clinical fit

What this tool is for

Start with the authorized purpose, then verify how it fits your service line and reading workflow.

Exact purpose: BoneView 1.1-US analyzes eligible 2D radiographs as a concurrent fracture-reading aid. Limb examinations apply to patients aged 2 years and older; pelvis, hip, femur, ribs, thoracic spine, and lumbosacral spine are limited to adults older than 21 years. Clinical users retain diagnostic and patient-management responsibility.

Intended users: Clinicians authorized to diagnose fractures in primary care, emergency medicine, urgent care, specialty care such as orthopedics, and radiologists reviewing radiographs.

Care setting and population: Primary care, emergency medicine, urgent care, specialty care, and radiology workflows for eligible adult and pediatric radiographs.

Workflow role: Concurrent detection and localization aid during radiograph interpretation; the clinical user makes the primary diagnosis and patient-management decision.

Required input: DICOM 2D radiographs in specified views for ankle, foot, knee, tibia/fibula, wrist, hand, elbow, forearm, humerus, shoulder, clavicle, pelvis, hip, femur, ribs, thoracic spine, and lumbosacral spine, subject to age-specific labeling.

Output and human action: A configurable summary image and processed result images with solid or dotted fracture bounding boxes, processing frames, finding counts, and out-of-indication cautions; results can be toggled while original images remain unchanged.

Limitations: Not indicated below age 2. Pelvis, hip, femur, ribs, thoracic spine, and lumbosacral spine are adult-only. Use is limited to the specified body parts and views; out-of-scope images can return NOT AVAILABLE. Results are concurrent decision support and do not replace clinical interpretation.

Regulatory identity

FDA record and catalog context

The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.

FDA submission: K222176

Modality: X-ray/Radiography

Anatomy: Spine

Clearance type: 510(k)

Decision date: 2023-03-02

FDA status: FDA-cleared

Implementation

Questions for IT, informatics, and operations

Use these fields to structure a vendor demo, security review, and implementation estimate.

Integration: BoneView receives studies from a DICOM source through an intermediate DICOM node and returns result files to a DICOM destination such as PACS or radiological equipment for viewing or onward transfer. Source and destination can differ.

Deployment and data flow: On-premise or cloud deployment connected to computing platforms, X-ray systems, or PACS, as described in the exact FDA comparison table.

Security and privacy: The exact FDA comparison table labels the device HIPAA compliant; it does not disclose the control scope, audit period, encryption, access-control, vulnerability-management, or incident-response evidence needed for procurement review.

Training and support: Vendor documentation pending

Monitoring and change control: Monitor age and body-part eligibility, supported-view routing, NOT AVAILABLE results, bounding-box operating point, DICOM delivery, disagreements and overrides, false negatives and false positives, downstream imaging/referrals, downtime, updates, complaints, and exact-submission recalls.

Exact DICOM source-to-destination workflow

The exact packet describes automatic receipt through an intermediate DICOM node and return of summary/result images to a potentially different DICOM destination for PACS or equipment viewing.

exact submission · checked 2026-09-08

Source

Current BoneView family workflow

Gleamer's current US BoneView page describes automatic second reading of trauma X-rays integrated into the reading workflow for adults and children over age 2. Current family claims are not used to broaden the exact K222176 body-part, view, or age labeling.

product family · checked 2026-09-08

Source

NICE evidence-generation controls

NICE HTG739 calls for clear local disagreement protocols and evidence collection on diagnostic accuracy, costs, referrals, treatment changes, software failures, subgroup performance, implementation costs, and postmarket surveillance during conditional NHS use.

product family · checked 2026-09-08

Source

Evidence

Performance evidence

Metrics are shown only when they are tied to a source, endpoint, population, and tested product version.

Evidence summary: The exact submission adds pediatric indications using a 2,000-radiograph standalone study and references the unchanged algorithm's earlier 24-reader, 480-case adult MRMC study. Pediatric operating points and adult aided-reader endpoints are kept distinct.

Reported sensitivity: Pediatric standalone: 90.9% at the high-sensitivity operating point and 79.2% at the high-specificity operating point; adult carried-forward MRMC aided sensitivity: 75.2%.

Reported specificity: Pediatric standalone: 82.1% at the high-sensitivity operating point and 96.5% at the high-specificity operating point; adult carried-forward MRMC aided specificity: 95.6%.

Pediatric high-sensitivity operating-point sensitivity

90.9 percent

Examination-level fracture sensitivity at DOUBT FRACT operating point in 2,000 radiographs from patients aged 2-21 years; 1,000 positive and 1,000 negative examinations.

Tested version: BoneView 1.1-US configuration described in K222176

Source

Pediatric high-sensitivity operating-point specificity

82.1 percent

Examination-level fracture specificity at DOUBT FRACT operating point in 2,000 radiographs from patients aged 2-21 years; 1,000 positive and 1,000 negative examinations.

Tested version: BoneView 1.1-US configuration described in K222176

Source

Pediatric high-specificity operating-point specificity

96.5 percent

Examination-level fracture specificity at FRACT operating point in 2,000 radiographs from patients aged 2-21 years; 1,000 positive and 1,000 negative examinations.

Tested version: BoneView 1.1-US configuration described in K222176

Source

Pediatric high-specificity operating-point sensitivity

79.2 percent

Examination-level fracture sensitivity at FRACT operating point in 2,000 radiographs from patients aged 2-21 years; 1,000 positive and 1,000 negative examinations.

Tested version: BoneView 1.1-US configuration described in K222176

Source

Adult carried-forward aided-reader sensitivity

75.2 percent

Reader fracture-detection sensitivity with BoneView assistance in 480 adult cases interpreted by 24 readers in the predicate MRMC study.

Tested version: Unchanged BoneView algorithm carried forward in K222176 from K212365

Source

Adult carried-forward aided-reader specificity

95.6 percent

Reader fracture-detection specificity with BoneView assistance in 480 adult cases interpreted by 24 readers in the predicate MRMC study.

Tested version: Unchanged BoneView algorithm carried forward in K222176 from K212365

Source

K222176 BoneView pediatric standalone validation

Standalone fracture-detection performance comparison between pediatric and adult datasets at prespecified high-sensitivity and high-specificity operating points. · 2,000 radiographs from patients aged 2-21 years, balanced between fracture-positive and fracture-negative examinations and spanning the pediatric-labeled anatomy and eight manufacturers.

exact submission · Tested version: BoneView 1.1-US configuration described in K222176 · n=2000 · Sponsor or vendor study

K222176

The packet states the pediatric dataset was separate from training, tuning, and operating-point data. Dataset separation does not establish independent investigators.

Source

BoneView adult MRMC study carried forward in K222176

Fully crossed retrospective multiple-reader, multiple-case study with aided and unaided sessions separated by at least one month. · 480 adult cases interpreted by 24 clinical readers, with a three-US-board-certified-radiologist reference standard and multiple manufacturers.

exact submission · Tested version: Unchanged BoneView algorithm carried forward in K222176 from K212365 · n=480 · Sponsor or vendor study

K222176 · K212365

The K222176 summary says no new clinical study was conducted and carries this predicate study forward because the algorithm was unchanged.

Source

Economics and lifecycle

Budget and ongoing governance

These are common procurement questions; unknown values remain visible until a source supports them.

Pricing and total cost: Not established in reviewed sources

Reimbursement and coding: Not established in reviewed sources

No product-specific code

NICE HTG739 conditionally recommends BoneView for NHS use during a two-year evidence-generation period, subject to evidence-generation agreements and appropriate regulatory and DTAC approval; this is not a reimbursement determination.

NICE guidance for the NHS in England · England · Effective 2025-01-14

NICE's exploratory model uses GBP 1 per scan and states actual software, implementation, and postmarket costs are uncertain. Treat that figure as a health-technology-model assumption, not a vendor quote.

Source

Safety and lifecycle

Postmarket record

Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.

Postmarket safety review: The exact-submission FDA recall query returned no native recall record for K222176. This limited query does not establish absence of recalls or other safety information.

Buyer worksheet

Open questions to take to the vendor

Verify training: Exact-version onboarding, role-based training, competency checks, support response, and retraining after updates were not established.
Verify pricing and total cost: NICE's GBP 1-per-scan figure is an exploratory model assumption, not a BoneView quote or public list price.
Verify reimbursement and coding relevance: NICE HTG739 is conditional English NHS adoption guidance, not a payer coverage or product-specific reimbursement determination.

Open evaluation checklist

Research record

What has been checked

This audit distinguishes completed source review from fields that have not yet been researched.

Human reviewedStatus

2026-09-08Last searched

26Fields reviewed

12Source classes checked

20Reviewed PubMed leads

6Reviewed trial leads

0Unreviewed FDA recall leads

Stored PubMed and trial candidates were screened by identifier and metadata only. None was promoted without full-text or registry-record review; this is not a systematic evidence review. The current discovery snapshot contains 20 PubMed and 6 ClinicalTrials.gov candidate records; its dated, count-matched human screening remains current. Unlinked candidates remain quarantined. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.

Candidate leads were screened against the exact product and tested version. Unlinked records remain quarantined.

Source classes: fda ai list, fda decision summary, acr ai central product, vendor product page, health technology guidance, fda device recall, literature index, trial registry, stored candidate metadata, pubmed, clinical trials, openfda device recall

Sources

Source ledger

Sources accessed through 2026-09-08.

K222176 FDA decision source U.S. Food and Drug Administration · 2026-08-31
Artificial Intelligence-Enabled Medical Devices U.S. Food and Drug Administration · 2026-08-31
BoneView model card (K222176) American College of Radiology · 2026-09-01
PubMed biomedical literature index U.S. National Library of Medicine · 2026-09-01
ClinicalTrials.gov study registry U.S. National Library of Medicine · 2026-09-01
openFDA Device Recall API U.S. Food and Drug Administration · 2026-09-02
FDA 510(k) K222176: BoneView 1.1-US U.S. Food and Drug Administration · 2026-09-07
BoneView AI fracture detection Gleamer · 2026-09-08
NICE HTG739: AI technologies to help detect fractures on X-rays in urgent care National Institute for Health and Care Excellence · 2026-09-08
openFDA exact recall query for K222176 U.S. Food and Drug Administration · 2026-09-07

Alternatives

Related tools to compare

FDA-cleared K251078

AutoDensity

Eos Imaging

AutoDensity estimates L1-L4 spine bone-mineral density from EOSedge dual-energy AP radiographs for opportunistic orthopedic pre-surgical assessment; it is not a replacement for...

Modality: X-ray/Radiography
Anatomy: Spine
Decision: 2025-11-14

MSK and bone

FDA-cleared K241593

BoneMetrics (US)

Gleamer SAS

BoneMetrics is fully automated software that assists trained radiology professionals with Cobb-angle measurement on frontal spine radiographs in patients aged four years or older...

Modality: X-ray/Radiography
Anatomy: Spine
Decision: 2025-02-05

MSK and bone Quantification and segmentation

FDA-cleared K221632

Spine CAMP™

Medical Metrics, Inc.

Spine CMAP is a fully-automated software that analyzes X-ray images of the spine to produce reports that contain static and/or motion metrics. Spine CAMP can be used to obtain...

Modality: X-ray/Radiography
Anatomy: Spine
Decision: 2022-10-18

MSK and bone

FDA-cleared K212005

UNiD Spine Analyzer

MEDICREA International, Inc.

The UNiDTM Spine Analyzer is intended for assisting healthcare professionals in viewing and measuring images as well as planning orthopedic surgeries. The device allows surgeons...

Modality: X-ray/Radiography
Anatomy: Spine
Decision: 2022-01-12

MSK and bone Quantification and segmentation