Radiology AI Directory

FDA-cleared profile

DeepXray

Alpha Intelligence Manifolds, Inc.

DeepXray is a fully automated CR or DX radiographic image-processing device intended to aid trained medical professionals in measuring minimum joint-space width, assessing sclerosis, joint-space narrowing, and osteophytes under OARSI criteria, and assessing radiographic knee osteoarthritis under Kellgren-Lawrence grading of standing fixed-flexion knee radiographs. It must not replace full patient evaluation or be relied on alone for diagnosis.

X-ray/Radiography workflow
Evidence status: each field states its source quality, applicability, and review date. Research pending, information not established, and vendor documentation pending remain distinct outcomes.

Clinical details

What this tool is for

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

Exact purpose
DeepXray is a fully automated CR or DX radiographic image-processing device intended to aid trained medical professionals in measuring minimum joint-space width, assessing sclerosis, joint-space narrowing, and osteophytes under OARSI criteria, and assessing radiographic knee osteoarthritis under Kellgren-Lawrence grading of standing fixed-flexion knee radiographs. It must not replace full patient evaluation or be relied on alone for diagnosis.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Intended users
Trained radiologists, orthopedists, physicians, and medical technicians.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Care setting and population
Clinical radiographic review workflows using supported standing knee radiographs.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Workflow role
Automated knee radiograph measurement and osteoarthritis feature assessment to aid professional review.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Required input
Computed or directly digital standing, fixed-flexion knee radiographs in CR or DX format.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Output and human action
Minimum joint-space width, femoral-tibial angle, Kellgren-Lawrence grade, OARSI feature assessments, quality warnings, and an editable web report.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Limitations
The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04

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
K223621
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
X-ray/Radiography
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Anatomy
Knee; radiographic osteoarthritis features
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2023-09-08
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
FDA status
FDA-cleared
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31

Implementation

Questions for IT, informatics, and operations

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

Integration
The FDA package describes CR or DX radiograph input, DICOM viewing beside the original radiograph, a browser-based editable report, quality warnings, markup images, and saved or output reports.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04

This is the interface boundary described in the exact FDA package; current local compatibility, routing, identity, archive, and downtime behavior still require acceptance testing.

Deployment and data flow
The FDA package describes operation in Docker containers on a Linux server with a web-browser report; current hosting, security, service, availability, and local deployment remain unverified.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04

This is the release-level boundary described in the exact FDA package; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence.

Security and privacy
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-04

Public materials reviewed for this exact release do not establish the complete security posture. Request data-flow, identity, audit, encryption, retention, remote-access, vulnerability-management, backup, and incident-response evidence.

Training and support
Only trained radiologists, orthopedists, physicians, and medical technicians should operate or interpret the product. Local onboarding should cover the exact release, supported population, limitations, failure examples, escalation, downtime, and competency documentation.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Monitoring and change control
Monitor K223621 by exact hardware, software, model, and algorithm version; patient population; anatomy; protocol; operator; input quality; output edits or overrides; failed studies; repeat acquisition or rework; downstream impact; downtime; incidents; recalls; and updates. Track these product-specific limits: The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04

This is buyer-facing monitoring guidance derived from the exact cleared or authorized scope; it is not a claim that the FDA package provides a live monitoring service.

Release and scope verification

Map installed model, build, options, population, anatomy, inputs, outputs, and enabled functions to K223621 before acceptance.

exact submission · checked 2026-09-04

Later product-family features are not evidence that this cleared or authorized release includes them.

Source

Deployment boundary

The FDA package describes operation in Docker containers on a Linux server with a web-browser report; current hosting, security, service, availability, and local deployment remain unverified.

exact submission · checked 2026-09-04

FDA-described deployment boundaries do not establish current hosting contracts, security controls, uptime, or local qualification.

Source

Interoperability acceptance

The FDA package describes CR or DX radiograph input, DICOM viewing beside the original radiograph, a browser-based editable report, quality warnings, markup images, and saved or output reports.

exact submission · checked 2026-09-04

Test representative identifiers, orientation, geometry, measurements, units, routing, failure handling, and round trips locally.

Source

Clinical acceptance

Use a signed local test set for the supported population and workflow. Include common and difficult cases, exclusions, acquisition variation, failed or low-quality inputs, reviewer overrides, and downstream effects. The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.

exact submission · checked 2026-09-04

Define stop-use, escalation, rollback, and revalidation triggers before production use.

Source

Economic evaluation

Model capital and recurring cost against net staff time after review, throughput, repeat imaging or rework, room time, consumables, infrastructure, training, service, downtime, upgrade, and replacement costs.

product family · checked 2026-09-04

No exact-product price was found in the reviewed public material; productivity or value claims require local evidence.

Source

Lifecycle monitoring

Monitor K223621 by exact hardware, software, model, and algorithm version; patient population; anatomy; protocol; operator; input quality; output edits or overrides; failed studies; repeat acquisition or rework; downstream impact; downtime; incidents; recalls; and updates. Track these product-specific limits: The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.

exact submission · checked 2026-09-04

Revalidate after material software, hardware, model, protocol, interface, or clinical-policy changes. knee radiograph osteoarthritis analysis software limits remain submission-specific.

Source

Evidence

Performance evidence

Metrics are shown only when they are tied to a source, endpoint, population, and tested product version. Candidate literature without exact product and version linkage is not shown as product evidence.

Evidence summary
K223621 FDA decision material identifies the exact knee radiograph osteoarthritis analysis software, labeled use, and submission-specific verification or approval evidence. It does not establish product-wide sensitivity, specificity, outcomes, or independent clinical validation beyond the exact evidence summarized here.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-04
Reported sensitivity
87%
  • Public source
  • Exact FDA submission
  • Checked 2026-09-01

Model sensitivity reported by ACR AI Central. Review endpoint, threshold, study population, and tested version before comparison.

Reported specificity
84%
  • Public source
  • Exact FDA submission
  • Checked 2026-09-01

Model specificity reported by ACR AI Central. Review endpoint, threshold, study population, and tested version before comparison.

Kellgren-Lawrence grade sensitivity

0.87 proportion

  • EndpointSensitivity for KL grade >= 2
  • Population11,775 knees from 6,114 DICOM studies and 1,121 subjects
  • Tested versionDeepXray configuration described in K223621
Source

Kellgren-Lawrence grade specificity

0.84 proportion

  • EndpointSpecificity for KL grade >= 2
  • Population11,775 knees from 6,114 DICOM studies and 1,121 subjects
  • Tested versionDeepXray configuration described in K223621
Source

Joint-space narrowing sensitivity

0.88 proportion

  • EndpointSensitivity for OARSI grade >= 1
  • Population11,775 knees from 6,114 DICOM studies and 1,121 subjects
  • Tested versionDeepXray configuration described in K223621
Source

Joint-space narrowing specificity

0.82 proportion

  • EndpointSpecificity for OARSI grade >= 1
  • Population11,775 knees from 6,114 DICOM studies and 1,121 subjects
  • Tested versionDeepXray configuration described in K223621
Source

K223621 FDA evidence package for DeepXray

  • DesignFDA 510(k) performance evaluation using a longitudinal Osteoarthritis Initiative test dataset with adjudicated labels and reference measurements.
  • PopulationKnee; radiographic osteoarthritis features
  • Scopeexact submission
  • Tested versionDeepXray configuration described in K223621
  • Samplen=1121
  • IndependenceSponsor or vendor study

K223621

The FDA summary also reports osteophyte and sclerosis metrics and measurement regressions; four status metrics are promoted here to keep the dossier concise. The source states that automated quality control blocked 0.3% of test samples.

Source

Costs and setup

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
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-04

No public list price for the exact cleared or authorized configuration was found. Obtain a written quote separating hardware or license basis, implementation, interfaces, infrastructure, training, service, upgrades, renewal, consumables, and exit costs.

Reimbursement and coding
No separate named-product Medicare payment was identified in the reviewed CMS coverage material. Evaluate the product within the applicable imaging or clinical service line and verify payer, site-of-service, coding, and coverage assumptions independently.
  • Public source
  • Not applicable
  • Checked 2026-09-04

No product-specific code

No separate named-product payment identified in reviewed public material

Centers for Medicare & Medicaid Services · United States

This is not a product-specific reimbursement determination. Build a local total-cost and value model and verify payer, site-of-service, coding, and coverage assumptions independently.

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 2026-09-02 openFDA device-recall snapshot contained no record matched to K223621 by exact native submission identifier. This does not exclude product-family, later-version, or adverse-event information.
  • Public source
  • Exact FDA submission
  • Checked 2026-09-04

Exact-identifier review does not prove absence of all product-family safety signals.

Buyer worksheet

Open questions to take to the vendor

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
2026-09-04Last searched
26Fields reviewed
12Source classes checked
5Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads

Five PubMed records were screened. Two concern the different DeepXray Spina bone-density product and three are unrelated legacy uses of the phrase deep X-ray; none evaluates the K223621 knee-osteoarthritis product and version, so all five are quarantined. The current discovery snapshot contains 5 PubMed and 0 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, fda decision material, fda pma record, peer reviewed literature, clinical trial registry, reimbursement policy, fda device recall, pubmed, clinical trials, openfda device recall

Sources & history

How this profile was documented

Open the ledger for source dates, scope, and research-record updates.

View source ledger and history

Source ledger

  1. FDA 510(k) K223621: DeepXray

    U.S. Food and Drug Administration - Published 2023-09-08 - Accessed 2026-09-04

    Scope: identity, purpose, clinicalUse, modality, anatomy, intendedUsers, careSetting, workflowRole, input, output, limitations, evidenceSummary

  2. Artificial Intelligence-Enabled Medical Devices

    U.S. Food and Drug Administration - Accessed 2026-08-31

    Scope: regulatoryIdentity, modalityContext

  3. DeepXray model card (K223621)

    American College of Radiology - Published 2026-08-17 - Accessed 2026-09-01

    Scope: intendedUsers, output, limitations, reportedSensitivity, reportedSpecificity, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities

  4. PubMed biomedical literature index

    U.S. National Library of Medicine - Accessed 2026-09-01

    Scope: evidenceDiscovery

  5. ClinicalTrials.gov study registry

    U.S. National Library of Medicine - Accessed 2026-09-01

    Scope: evidenceDiscovery, studyStatus

  6. Medicare Coverage Database

    Centers for Medicare & Medicaid Services - Accessed 2026-09-01

    Scope: coverage, codingContext

  7. openFDA Device Recall API

    U.S. Food and Drug Administration - Accessed 2026-09-02

    Scope: recallDiscovery, nativeSubmissionMatching

Research history

  1. K223621 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    human reviewed

Alternatives

Related tools to compare

FDA-cleared K253172

MediAI-OA

Crescom Co., Ltd.

Assist trained professionals in assessing radiographic knee osteoarthritis and its sclerosis, joint-space-narrowing, and osteophyte features on standing fixed-flexion knee...

Modality
X-ray/Radiography
Anatomy
Knee joint
Decision
2026-06-15
X-ray/Radiography workflow
FDA-cleared K253930

Overjet Iris Intelligent Imaging System

Overjet, Inc.

Overjet Iris is a web-based dental PACS for storing, viewing, and supporting image-quality review of two-dimensional intraoral radiographs, panoramic images, and color photographs.

Modality
X-ray/Radiography
Anatomy
Teeth and maxillofacial anatomy
Decision
2026-04-10
X-ray/Radiography workflow
FDA-cleared K250525

Second Opinion® Panoramic

Pearl, Inc.

Second Opinion Panoramic is an automated image-processing aid that identifies and marks regions of interest for caries, periapical radiolucency, and impacted third molars on...

Modality
X-ray/Radiography
Anatomy
Permanent teeth; caries, periapical radiolucency, and impacted third molars
Decision
2025-11-14
X-ray/Radiography workflow
FDA-cleared K251002

Videa Dental AI

VideaHealth Inc.

Analyzes bitewing, periapical, and panoramic intraoral radiographs from patients aged 3 years and older to identify and localize specified suspected dental findings, historical...

Modality
X-ray/Radiography
Anatomy
Dental/Maxillofacial
Decision
2025-09-19
X-ray/Radiography workflow