Radiology AI Directory

FDA-cleared profile

AI-Rad Companion (Cardiovascular)

Siemens Medical Solutions U.S.A.

Adjunctive cardiovascular review for radiologists and physicians in emergency medicine, specialty care, urgent care and general practice, including heart volume, coronary calcium volume, aortic segmentation, aortic diameter measurement and threshold-based highlighting of enlarged diameters.

Cardiac imagingQuantification and segmentation
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
Adjunctive cardiovascular review for radiologists and physicians in emergency medicine, specialty care, urgent care and general practice, including heart volume, coronary calcium volume, aortic segmentation, aortic diameter measurement and threshold-based highlighting of enlarged diameters.
FDA source Exact product version Checked 2026-09-07
Intended users
Radiologists and qualified physicians in emergency medicine, specialty care, urgent care and general practice.
FDA source Exact product version Checked 2026-09-07
Care setting and population
Clinical radiology and physician-care settings using previously acquired adult CT examinations, including emergency, urgent, specialty and general practice workflows.
FDA source Exact product version Checked 2026-09-07
Workflow role
Adjunctive quantitative and qualitative clinical decision support for qualified clinicians; outputs support interpretation and assessment and do not replace professional review.
FDA source Exact product version Checked 2026-09-07
Required input
Previously acquired DICOM CT images from adult patients. FDA validation covered non-cardiac chest CT with filtered-backprojection reconstruction from Siemens, GE, Philips and Toshiba/Canon systems; calcium detection also included Siemens iterative reconstruction.
FDA source Exact product version Checked 2026-09-07
Output and human action
Heart segmentation and volume, total coronary calcium volume, aorta segmentation, aortic diameters at predefined and maximum-diameter locations, threshold-based diameter categories/highlighting, quantitative and textual reports, DICOM Secondary Capture and DICOM Structured Report TID 1500 outputs.
FDA source Exact product version Checked 2026-09-07
Limitations
Only adult DICOM input is labeled in the exact submission. The validated CT reconstruction, scanner, slice and image-quality conditions limit direct generalization; the submission states that no clinical tests were conducted for the introduced modifications, with verification and validation used instead. Outputs require qualified-clinician review.
FDA source Exact product version Checked 2026-09-07

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
K222360
FDA source Exact FDA submission Checked 2026-08-31
Modality
CT/CTA
FDA source Exact product version Checked 2026-09-07
Anatomy
Heart/Cardiovascular
FDA source Exact product version Checked 2026-09-07
Clearance type
510(k)
FDA source Exact FDA submission Checked 2026-08-31
Decision date
2023-04-06
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 exact submission describes DICOM CT input and forwarding of quantitative, structured and textual reports plus DICOM Secondary Capture to PACS; VA20 adds a human- and machine-readable DICOM Structured Report using TID 1500.
FDA source Exact product version Checked 2026-09-07
Deployment and data flow
The VA20 submission describes both cloud and edge on-premise deployments; the edge configuration processes data and results in the customer environment while remaining connected to the cloud for monitoring and maintenance.
FDA source Exact product version Checked 2026-09-07
Security and privacy
Vendor documentation pending
Vendor confirmation Exact product version Checked 2026-09-07

The reviewed sources do not establish exact VA20 security controls, retention or assurance documentation.

Training and support
Vendor documentation pending
Vendor confirmation Exact FDA submission Checked 2026-08-13

Training, onboarding, competency, and support commitments are commercial implementation details that require current vendor documentation.

Monitoring and change control
Vendor documentation pending
Vendor confirmation Exact FDA submission Checked 2026-08-13

Local acceptance testing, production monitoring, drift review, update control, and incident escalation require a current vendor and site-specific governance plan.

Cloud and edge/on-premise deployment

The VA20 submission describes cloud and edge on-premise deployments, with edge processing in the customer environment while remaining connected to the cloud for monitoring and maintenance.

exact product version · checked 2026-09-07
Source

Structured and PACS-ready reporting

VA20 generates quantitative, structured and textual reports, DICOM Secondary Capture and a human- and machine-readable DICOM Structured Report using TID 1500 for transfer to clinical systems.

exact product version · checked 2026-09-07
Source

Family PACS/web review workflow

Siemens' current family whitepaper describes reconstructed thorax CT being sent to PACS and in parallel to AI-Rad Companion, with results delivered to web-based review or directly to PACS and used with original data for reporting.

product family · checked 2026-09-07

The reviewed whitepaper covers current VA40A/VA22A family material; it does not establish that every feature or connector is present in K222360 VA20.

Source

Review, accept/decline and send-to-PACS interaction

The Siemens cardiovascular job aid shows calcium and heart-volume findings, nine aortic landmarks with diameters and threshold-based color coding; users can accept or decline findings before sending the case to PACS.

product family · checked 2026-09-07

This is 2019 training material, explicitly not an operator manual and not necessarily current; optional functions and country availability require confirmation.

Source

Evidence

Performance evidence

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

Evidence summary
FDA validation reported subject aorta-segmentation Dice 0.924 ± 0.046 in 315 retrospective cases. In 193 cases, including 50% with dilated aorta and 9% with aortic aneurysm, subject aortic diameter bias at nine landmarks was within ±1.5 mm and MAE was at most 2.2 mm; maximum ascending/descending aorta measurements had 95% limits of agreement ±3.51 mm with 91.9% within those limits.
FDA source Exact product version Checked 2026-09-07
Reported sensitivity
Not established in reviewed sources
Reviewed sources checked Exact product version Checked 2026-09-07

The exact FDA endpoints are segmentation and measurement agreement, not disease-detection sensitivity.

Reported specificity
Not established in reviewed sources
Reviewed sources checked Exact product version Checked 2026-09-07

The exact FDA endpoints are segmentation and measurement agreement, not disease-detection specificity.

Aorta segmentation Dice

0.924 Dice coefficient

Aorta segmentation overlap in Representative retrospective clinical cohort.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Nine-landmark aortic diameter bias absolute bound

1.5 mm absolute bound

Bias of aortic diameter measurements at nine predefined landmarks in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Nine-landmark aortic diameter MAE upper bound

2.2 mm upper bound

Mean absolute error of aortic diameter measurements at nine predefined landmarks in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Maximum ascending/descending aorta LoA absolute bound

3.51 mm absolute bound

95% limits of agreement for maximum ascending and descending aortic diameter measurements in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Maximum ascending/descending aorta measurements within LoA

0.919 proportion

Measurements within the FDA-reported 95% limits of agreement in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Maximum ascending/descending aorta bias absolute bound

1.5 mm absolute bound

Bias of maximum ascending and descending aortic diameter measurements in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

Maximum ascending/descending aorta MAE upper bound

1.8 mm upper bound

Mean absolute error of maximum ascending and descending aortic diameter measurements in Representative retrospective clinical cohort including 50% dilated-aorta and 9% aortic-aneurysm cases.

Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360
Source

AI-Rad Companion (Cardiovascular) aorta segmentation validation

Representative retrospective clinical cohort validation of the updated aorta-segmentation algorithm against the predicate device. · 315 adult CT cases with subgroup evaluation across manufacturers, slice thickness, sex, age and comorbidities.

exact product version · Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360 · n=315 · Sponsor or vendor study

K222360

The FDA summary reports average Dice 0.924 ± 0.046 for the subject and 0.910 ± 0.066 for the predicate.

Source

AI-Rad Companion (Cardiovascular) aortic diameter validation

Representative retrospective clinical cohort with Bland-Altman analysis of nine predefined landmarks and maximum ascending/descending aorta measurements. · 193 adult CT cases, including 50% with dilated aorta and 9% with aortic aneurysm.

exact product version · Tested version: AI-Rad Companion (Cardiovascular) VA20 submitted in K222360 · n=193 · Sponsor or vendor study

K222360

The submission states that no clinical tests were conducted for the introduced modifications; the reported evidence is clinical-data-based software validation and verification/validation.

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
Vendor documentation pending
Vendor confirmation Exact product version Checked 2026-09-07

No public price or quote for the exact VA20 configuration was reviewed.

Reimbursement and coding
Research pending
Needs research Exact product version Checked 2026-09-07

Payer policy research was outside this worker's scope.

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
Not established in reviewed sources
Reviewed sources checked Exact product version Checked 2026-09-07

The exact-ID recall packet contained zero records; this limited result does not establish absence of recall or safety information.

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.

Exact FDA record reviewedStatus
2026-09-07Last searched
23Fields reviewed
11Source classes checked
20Reviewed PubMed leads
1Reviewed trial leads
0Unreviewed FDA recall leads

Stored candidate metadata was screened. The broad AI-Rad Companion query returned 20 PubMed and one trial identifier without exact K222360 VA20 linkage established in metadata; no full paper or trial record was reviewed, and no candidate is promoted as product evidence. The current discovery snapshot contains 20 PubMed and 1 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 technical documentation, vendor training material, stored candidate metadata, literature index, trial registry, pubmed, clinical trials, openfda device recall

Sources

Source ledger

Sources accessed through 2026-09-08.

Alternatives

Related tools to compare

FDA-cleared K252217

CT VScore+

Canon Medical Informatics, Inc.

CT VScore+ evaluates calcified coronary lesions on ECG-gated, non-contrast cardiac CT in patients aged 30 years or older, automatically generating coronary calcium scores and...

Modality
CT/CTA
Anatomy
Heart/Cardiovascular
Decision
2025-11-28
Cardiac imagingQuantification and segmentation