FDA-cleared profile

CINA

AVICENNA.AI · CT/CTA · FDA-cleared (510(k))

Authorized purpose: CINA analyzes non-enhanced head CT and head CTA DICOM in parallel with standard interpretation to flag suspected intracranial hemorrhage and anterior-circulation large-vessel occlusion (distal ICA, MCA-M1 or proximal MCA-M2), issuing worklist and active notifications with informational previews for trained-radiologist triage; it does not diagnose or alter original images.

Clinical role
Parallel worklist prioritization and notification for suspected ICH or anterior-circulation LVO; not a diagnostic device or replacement for standard interpretation.
Images and patients
CT/CTA · Brain
Key limitation
Keep in mind: LVO scope is limited to distal ICA, MCA-M1, or proximal MCA-M2 in the anterior circulation. Notifications and compressed previews are informational only, do not localize the finding, and require review of the full original images with other patient information.

Overview status: Source-reviewed overview

Report a correction
Clinical details Purpose, workflow fit, evidence, and safety record

Workflow navigation pilot

Workflow role has not yet been reviewed for this navigation pilot.

A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources

  • What does this software do?Authorized purpose: CINA analyzes non-enhanced head CT and head CTA DICOM in parallel with standard interpretation to flag suspected intracranial hemorrhage and anterior-circulation large-vessel occlusion (distal ICA, MCA-M1 or proximal MCA-M2), issuing worklist and active notifications with informational previews for trained-radiologist triage; it does not diagnose or alter original images.
  • Which images or clinical context are in scope?Modality: CT/CTA Anatomy or clinical context: Brain Input: DICOM non-enhanced head CT for the ICH application and DICOM head CTA for the LVO application, subject to the recommended acquisition protocols.
  • Who uses it?Intended users: Hospital networks and trained radiologists; notified clinicians remain responsible for full-image review and professional judgment.
  • What does the software produce?Output: Active pop-up and passive worklist notifications identifying the suspected finding type, plus a small compressed unannotated grayscale preview marked not for diagnostic use; original images are not altered.
  • What is its most important limitation?Key limitation: LVO scope is limited to distal ICA, MCA-M1, or proximal MCA-M2 in the anterior circulation. Notifications and compressed previews are informational only, do not localize the finding, and require review of the full original images with other patient information.

Clinical takeaway. Clinical role: CINA analyzes non-enhanced head CT and head CTA DICOM in parallel with standard interpretation to flag suspected intracranial hemorrhage and anterior-circulation large-vessel occlusion (distal ICA, MCA-M1 or proximal MCA-M2), issuing worklist and active notifications with informational previews for trained-radiologist triage; it does not diagnose or alter original images.

Evidence takeaway. Evidence from the reviewed source record: K221716 contains two separately sized retrospective validation cohorts: 814 NCCT cases for ICH and 476 CTA cases for LVO. Results are reported per application and are not pooled.

Evidence context

Evidence context not reviewed for this FDA record.

Public-label constraints

Label constraints have not been reviewed for this exact FDA record. Unknown is not all ages or evidence of unsuitability.

Public-label constraints, not patient-level eligibility or a medical recommendation. Training and evaluation populations are separate. Read the original labeling and confirm the exact release and protocol.

Purpose
CINA analyzes non-enhanced head CT and head CTA DICOM in parallel with standard interpretation to flag suspected intracranial hemorrhage and anterior-circulation large-vessel occlusion (distal ICA, MCA-M1 or proximal MCA-M2), issuing worklist and active notifications with informational previews for trained-radiologist triage; it does not diagnose or alter original images.
  • Exact FDA submission
  • Checked 2026-09-08
Workflow role
Parallel worklist prioritization and notification for suspected ICH or anterior-circulation LVO; not a diagnostic device or replacement for standard interpretation.
  • Exact FDA submission
  • Checked 2026-09-08
Required input
DICOM non-enhanced head CT for the ICH application and DICOM head CTA for the LVO application, subject to the recommended acquisition protocols.
  • Exact FDA submission
  • Checked 2026-09-08
Output and clinician action
Active pop-up and passive worklist notifications identifying the suspected finding type, plus a small compressed unannotated grayscale preview marked not for diagnostic use; original images are not altered.
  • Exact FDA submission
  • Checked 2026-09-08
Care setting
Hospital radiology networks using head CT and CTA worklists for acute neurovascular triage.
  • Exact FDA submission
  • Checked 2026-09-08
Intended users
Hospital networks and trained radiologists; notified clinicians remain responsible for full-image review and professional judgment.
  • Exact FDA submission
  • Checked 2026-09-08
Limitations
LVO scope is limited to distal ICA, MCA-M1, or proximal MCA-M2 in the anterior circulation. Notifications and compressed previews are informational only, do not localize the finding, and require review of the full original images with other patient information.
  • Exact FDA submission
  • Checked 2026-09-08
Evidence summary
K221716 contains two separately sized retrospective validation cohorts: 814 NCCT cases for ICH and 476 CTA cases for LVO. Results are reported per application and are not pooled.
  • Exact FDA submission
  • Checked 2026-09-08

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
K221716 contains two separately sized retrospective validation cohorts: 814 NCCT cases for ICH and 476 CTA cases for LVO. Results are reported per application and are not pooled.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-08
Reported sensitivity
ICH 91.4% (95% CI 87.2%-94.5%); LVO 97.9% (95% CI 94.6%-99.4%)
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-08
Reported specificity
ICH 97.5% (95% CI 95.8%-98.6%); LVO 97.6% (95% CI 95.1%-99.0%)
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-08

ICH sensitivity

91.4 percent

  • EndpointSuspected ICH triage sensitivity against concurrence of three US-board-certified neuroradiologists
  • Population814 anonymized non-contrast head CT cases; 255 ICH-positive
  • Tested versionCINA ICH/LVO triage configuration described in K221716

ICH specificity

97.5 percent

  • EndpointSuspected ICH triage specificity against concurrence of three US-board-certified neuroradiologists
  • Population814 anonymized non-contrast head CT cases
  • Tested versionCINA ICH/LVO triage configuration described in K221716

LVO sensitivity

97.9 percent

  • EndpointAnterior-circulation LVO triage sensitivity against concurrence of three US-board-certified neuroradiologists
  • Population476 anonymized head CTA cases; 188 LVO-positive
  • Tested versionCINA ICH/LVO triage configuration described in K221716

LVO specificity

97.6 percent

  • EndpointAnterior-circulation LVO triage specificity against concurrence of three US-board-certified neuroradiologists
  • Population476 anonymized head CTA cases
  • Tested versionCINA ICH/LVO triage configuration described in K221716

ICH mean time to notification

13.2 seconds

  • EndpointMean per-case time to notification
  • Population814 non-contrast head CT cases
  • Tested versionCINA ICH/LVO triage configuration described in K221716

LVO mean time to notification

25.8 seconds

  • EndpointMean per-case time to notification
  • Population476 head CTA cases
  • Tested versionCINA ICH/LVO triage configuration described in K221716

K221716 CINA ICH retrospective validation

  • DesignRetrospective blinded multicenter multinational standalone validation against concurrence of three US-board-certified neuroradiologists.
  • Population814 anonymized non-contrast head CT cases from three clinical sources (two US, one outside the US), including 255 ICH-positive cases and multiple scanner manufacturers.
  • Scopeexact submission
  • Tested versionCINA ICH/LVO triage configuration described in K221716
  • Samplen=814
  • Sites3
  • IndependenceSponsor or vendor study

K221716

Manufacturer-conducted FDA evidence; this is not an independent clinical-outcome study.

K221716 CINA LVO retrospective validation

  • DesignRetrospective blinded multicenter multinational standalone validation against concurrence of three US-board-certified neuroradiologists.
  • Population476 anonymized head CTA cases from three clinical sources, including 188 anterior-circulation LVO-positive cases and multiple scanner manufacturers.
  • Scopeexact submission
  • Tested versionCINA ICH/LVO triage configuration described in K221716
  • Samplen=476
  • Sites3
  • IndependenceSponsor or vendor study

K221716

Manufacturer-conducted FDA evidence; this is not an independent clinical-outcome study.

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 K221716. This limited query does not establish absence of recalls or other safety information and does not cover family or later-version records.
  • Public source
  • Exact FDA submission
  • Checked 2026-09-08
Pricing & contracts Public price, contract terms, and reimbursement

Price not public here; enter your quote

Not publicly available: Reviewed sources do not publish an exact-product procurement price with a stated offer scope.

Reimbursement

IT implementation Deployment, interfaces, data handling, and support

System and version relationships

Match the AI release, system build, configuration and region. Source documentation does not establish acceptance of an installed system.

No specific system/version pairing has completed review for this FDA record. A broad DICOM or product-family statement does not establish a named viewer build's support.

Review Merge, Visage, Sectra, AGFA and IntelePACS context

Integration chain: evidence at each hop

Public source context, not tested interoperability. Each hop needs its own release/configuration evidence. Missing or unavailable routes are not documented incompatibility. All local tests are planned, not passed; no installed-system acceptance is recorded.

Acquisition/source → routing → AI processing → returned objects → viewer/worklist/report → support owner

No specific route context has been source-reviewed for this record. Obtain both endpoint builds and documents; this is not a finding of incompatibility.

  1. Acquisition/source

    Source context, not route validation: DICOM non-enhanced head CT for the ICH application and DICOM head CTA for the LVO application, subject to the recommended acquisition protocols.

    Scope: Exact FDA submission.

    Confirm scanner/model, protocol, series completeness and both software builds.

    Field checked 2026-09-08 · FDA 510(k) K221716: CINA

  2. Routing

    Source context, not route validation: The on-premise CINA Platform exchanges DICOM with CT modalities, routers, and PACS, runs the ICH and LVO applications, and transfers result files for worklist prioritization. Local routing, identifiers, failure handling, and workstation behavior require acceptance testing.

    Scope: Exact FDA submission.

    Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.

    Field checked 2026-09-08 · FDA 510(k) K221716: CINA

  3. AI processing

    Source context, not route validation: On-premise server or workstation using a standard off-the-shelf operating environment and an on-premise Worklist Application.

    Scope: Exact FDA submission. This is the exact K221716 architecture; newer AVI Platform deployment claims are family context only.

    Confirm processing location, queue ownership, exclusions and exact AI build.

    Field checked 2026-09-08 · FDA 510(k) K221716: CINA

  4. Returned objects

    Source context, not route validation: Active pop-up and passive worklist notifications identifying the suspected finding type, plus a small compressed unannotated grayscale preview marked not for diagnostic use; original images are not altered.

    Scope: Exact FDA submission.

    Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.

    Field checked 2026-09-08 · FDA 510(k) K221716: CINA

  5. Viewer/worklist/report

    Unresolved route: Active pop-up and passive worklist notifications identifying the suspected finding type, plus a small compressed unannotated grayscale preview marked not for diagnostic use; original images are not altered.

    Scope: Exact FDA submission.

    Confirm the named viewer/worklist/report build, display behavior and report transfer. Output support alone does not establish this endpoint. The displayed source describes output, not validated end-to-end delivery.

    Field checked 2026-09-08 · FDA 510(k) K221716: CINA

  6. Support owner

    Unresolved route: Not established for the exact route.

    Scope: Scope not established.

    Name the local, platform and AI supplier support owners and escalation path.

Planned local route tests

No tests below have been performed or accepted.

  1. Patient/study identity (planned). Use approved non-patient test data to verify identifiers, accession and result-to-study linkage at every hop.
  2. Study completeness (planned). Test missing views/series, partial transfer, late arrivals, priors and unsupported acquisition inputs; confirm explicit refusal or fallback.
  3. Ordering and duplicates (planned). Send out-of-order, repeated and corrected studies; verify worklist order, deduplication and no misleading stale results.
  4. Report transfer (planned). Verify output object types, annotations, units, report content, destination and availability of original images.
  5. Access (planned). Verify authorized roles, audit trail, denied access and support ownership at each destination.
  6. Latency and failures (planned). Agree a workload and turnaround target; test queues, timeouts, missing results and fallback reading.
  7. Updates and rollback (planned). Define version change control, revalidation triggers, stop-use criteria and a tested rollback route.

Local implementation checklist

Agree the evidence and acceptance owner with your team and suppliers. Checkmarks apply to this page only and are not acceptance receipts.

Open the printable evaluation checklist

Deployment
On-premise server or workstation using a standard off-the-shelf operating environment and an on-premise Worklist Application.
  • Exact FDA submission
  • Checked 2026-09-08

This is the exact K221716 architecture; newer AVI Platform deployment claims are family context only.

Integration
The on-premise CINA Platform exchanges DICOM with CT modalities, routers, and PACS, runs the ICH and LVO applications, and transfers result files for worklist prioritization. Local routing, identifiers, failure handling, and workstation behavior require acceptance testing.
  • Exact FDA submission
  • Checked 2026-09-08
Security
Avicenna.AI's cybersecurity page states ISO/IEC 27001 certification by SGS, IEC 81001-5-1, TLS 1.2+ in transit, encryption at rest, role-based access with least privilege, and a HIPAA business associate agreement for US customers. Vendor-wide.
  • Vendor-wide
  • Checked 2026-10-25

Vendor statement, not an attestation; exact-release scope is not established.

Monitoring
Monitor protocol eligibility, DICOM receipt, per-application processing failures, notification latency, worklist delivery, false-negative and false-positive review, reader overrides, downtime, updates, complaints, and exact-submission recalls.
  • Exact FDA submission
  • Checked 2026-09-08

Buyer acceptance guidance derived from the exact workflow and validation endpoints; it is not a claimed vendor monitoring service.

Exact on-premise DICOM worklist path

The exact submission describes DICOM exchange among CT, routers or PACS, an on-premise CINA Platform and Worklist Application, and result files returned for worklist prioritization.

exact submission · checked 2026-09-08

Current AVI Platform family context

Avicenna.AI's 2025 AVI announcement describes automated PACS/RIS integration, centralized orchestration, and DICOM, HL7, and FHIR support for the current platform hosting the CINA portfolio. It also describes de-identification, encryption, access controls, and auditable operations. These are family claims and do not establish the exact K221716 deployment or assurance scope.

product family · checked 2026-09-08
Sources & review details FDA identity, research record, source ledger, and history

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
K221716
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
CT/CTA
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-08
Anatomy
Brain
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-08
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2022-11-22
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
FDA status
FDA-cleared
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31

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
20Screened PubMed leads
10Screened trial leads
0Unreviewed FDA recall leads

Stored exact-name candidate metadata was screened. The returned PubMed and trial records were unrelated to the CINA radiology product, so none was promoted; this is metadata triage, not a systematic literature review. The current discovery snapshot contains 20 PubMed and 10 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 documentation, vendor press release, fda device recall, literature index, trial registry, stored candidate metadata, pubmed, clinical trials, openfda device recall

Field review details

Recorded state, verification date, notes and sources for fields without a publishable value. Conflicting records stay explicitly unsettled here; no plain settled value is shown for them.

  • Public pricing: Not publicly available - checked 2026-09-08 - Exact FDA submission

    No public exact-version price, pricing unit, term, minimum, or implementation fee was established.

  • Pricing model: Not yet reviewed
  • Setup and integration fees: Not yet reviewed
  • Recurring fees: Not yet reviewed
  • Minimum commitment: Not yet reviewed
  • Contract duration: Not yet reviewed
  • Renewal terms: Not yet reviewed
  • Cancellation terms: Not yet reviewed
  • Support and service terms: Not yet reviewed
  • Trial or pilot terms: Not yet reviewed
  • Reimbursement: Not publicly available - checked 2026-10-26 - Exact FDA submission

    Bounded web search on 2026-10-26 (query: "Avicenna CINA reimbursement CPT"; top results reviewed) found no vendor or payer page stating coding, coverage or payment for this product. Avicenna's 2020-11-24 release describes NTAP eligibility for CINA Head (LVO triage); it does not tie that to this entry's clearance. This records what was found, not that none exists; eligibility depends on payer, site of service and use case.

  • Data hosting location: Not yet reviewed
  • Data retention: Not yet reviewed
  • Documented data use: Not yet reviewed
  • Hardware requirements: Not yet reviewed
  • Network requirements: Not yet reviewed
  • Identity and access: Not yet reviewed
  • Installation timeline: Not yet reviewed
  • Training: Not verified - checked 2026-09-08 - Exact FDA submission

    The indication requires trained radiologists, but exact-version training and competency requirements were not established.

9 sources - 3 history items

Source ledger

  1. FDA 510(k) K221716: CINA

    U.S. Food and Drug Administration - Accessed 2026-09-07

    Scope: identity, clinicalUse, modality, anatomy, intendedUsers, careSetting, workflowRole, input, output, limitations, integration, deployment, evidenceMetrics, evidenceStudies

  2. Artificial Intelligence-Enabled Medical Devices

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

    Scope: regulatoryIdentity, modalityContext

  3. CINA-ICH model card (K221716)

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

    Scope: purpose, modality, 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. openFDA Device Recall API

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

    Scope: recallDiscovery, nativeSubmissionMatching

  7. Avicenna.AI AVI Platform launch

    Avicenna.AI - Published 2025-11-13 - Accessed 2026-09-07

    Scope: productFamily, implementationCapabilities

  8. openFDA exact recall query for K221716

    U.S. Food and Drug Administration - Accessed 2026-09-07

    Scope: postmarketSafety

  9. Avicenna.AI Cybersecurity and Data Protection

    Avicenna.AI - Accessed 2026-10-25

    Scope: security

Research history

  1. K221716 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    human reviewed

  3. Reader overview source-reviewed

    Editorial review

    Source-reviewed editorial overlay

Alternatives

Related tools to compare

FDA-cleared K251590

Methinks CTA Stroke

Methinks Software S.L.

Authorized purpose: Methinks CTA Stroke analyzes acute-setting brain CT angiography in adults over 21 with suspected stroke for suspected large-vessel occlusion in the terminal ICA, MCA-M1, or MCA-M2 and sends PACS and/or specialist notifications in parallel to standard care; previews are informational and not diagnostic.

Modality
CT/CTA
Anatomy
Brain
Decision
2025-08-20
FDA-cleared K251151

Rapid CTA 360

iSchemaView

Authorized purpose: Rapid CTA 360 analyzes adult head CTA DICOM images to flag suspected large- and medium-vessel occlusion in specified intracranial and vertebral segments and notify trained clinicians for workflow triage; notifications are informational and not diagnostic.

Modality
CT/CTA
Anatomy
Brain
Decision
2025-07-16
FDA-cleared K250685

Methinks NCCT Stroke

Methinks Software S.L.

Authorized purpose: Methinks NCCT Stroke analyzes adult non-contrast head CT to flag suspected intracranial hemorrhage and suspected large-vessel occlusion of the ICA, MCA-M1, or MCA-M2 for parallel workflow triage via PACS and/or notifications; previews are informational, not diagnostic, and a negative notification does not rule out LVO or replace CTA/standard care.

Modality
CT/CTA
Anatomy
Brain
Decision
2025-06-16

Correct this exact record

Copy this public context and add the field, proposed wording and original source before sending. Nothing here is submitted automatically. Form-specific prefill has not been verified.

Open existing correction destination

Permission to display a submission is not evidence verification. A submission enters editorial review; it does not approve a public change. Form availability, data entry, receipt, review and publication are separate steps. Data entry and receipt remain unverified.

Accepted repository change history

No entry has been added to this scoped change history for this record. This is not proof that the record never changed.

Correction policy and limits · Public repository change history