Image and notification APIs
Image-receiver API, ingestion/analysis system, and output API connect image submission with institutional notification workflows.
exact submission · checked 2026-09-05FDA-cleared profile
ScreenDx
Imvaria, Inc
Authorized purpose: ScreenDx provides adjunctive positive/negative assessment of interstitial lung findings on DICOM lung CT in patients older than 22 years to support referral for clinical assessment; it does not rule in or rule out lung fibrosis or replace standard diagnosis.
Evidence status: each field states its source quality, applicability, and review date. Research pending, information not established, and vendor documentation pending remain distinct outcomes.
Product overview
Start with the essentials
Authorized purpose: ScreenDx provides adjunctive positive/negative assessment of interstitial lung findings on DICOM lung CT in patients older than 22 years to support referral for clinical assessment; it does not rule in or rule out lung fibrosis or replace standard diagnosis.
Overview status: Source-reviewed overview
- What does this software do? Authorized purpose: ScreenDx provides adjunctive positive/negative assessment of interstitial lung findings on DICOM lung CT in patients older than 22 years to support referral for clinical assessment; it does not rule in or rule out lung fibrosis or replace standard diagnosis.
- Which images or clinical context are in scope? Modality: CT/CTA Anatomy or clinical context: Chest/Lung Input: DICOM-compliant lung CT scans submitted through an image-receiver API; ingestion selects appropriate cases for analysis.
- Who uses it? Intended users: Clinicians qualified in the care of lung disease.
- What does the software produce? Output: Binary Positive (Suggestive of ILD)/Negative result; results are stored and transmitted by an output API to assigned users. No diagnostic information or image localization is generated.
- What is its most important limitation? Key limitation: Not a rule-in or rule-out test for lung fibrosis and not a replacement for current diagnostic methods. Use results with history, symptoms, other diagnostic tests, and professional judgment; age must be greater than 22 years.
Clinical takeaway
Clinical role: ScreenDx provides adjunctive positive/negative assessment of interstitial lung findings on DICOM lung CT in patients older than 22 years to support referral for clinical assessment; it does not rule in or rule out lung fibrosis or replace standard diagnosis.
Evidence takeaway
Evidence from the reviewed source record: Retrospective multicenter pivotal study of 3,018 unique patients, enriched to 23% positive lung-fibrosis diagnoses, using independently recorded clinical diagnoses as reference. The baseline reports sensitivity 91.4% and specificity 95.2%; an additional 2,482-case low-prevalence dataset is separately described in the FDA summary.
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
- ScreenDx provides adjunctive positive/negative assessment of interstitial lung findings on DICOM lung CT in patients older than 22 years to support referral for clinical assessment; it does not rule in or rule out lung fibrosis or replace standard diagnosis.
- Intended users
- Clinicians qualified in the care of lung disease.
- Care setting and population
- Hospital or clinic referral workflows; eligible patients are older than 22 years.
- Workflow role
- Adjunctive detection supporting referral and clinical assessment.
- Required input
- DICOM-compliant lung CT scans submitted through an image-receiver API; ingestion selects appropriate cases for analysis.
- Output and human action
- Binary Positive (Suggestive of ILD)/Negative result; results are stored and transmitted by an output API to assigned users. No diagnostic information or image localization is generated.
- Limitations
- Not a rule-in or rule-out test for lung fibrosis and not a replacement for current diagnostic methods. Use results with history, symptoms, other diagnostic tests, and professional judgment; age must be greater than 22 years.
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.
Implementation
Questions for IT, informatics, and operations
Use these fields to structure a vendor demo, security review, and implementation estimate.
- Integration
- Image Receiver API accepts cases from compliant systems such as DICOM/PACS. Output API integrates with hospital/clinic notification software such as an EHR or messaging system; the institution controls the output workflow.
Named interface protocols and local vendor-version compatibility are not established by these examples.
- Deployment and data flow
- Vendor documentation pending
FDA describes APIs and an ingestion/analysis system but does not establish the current customer's hosting topology, region, or retention terms.
- Security and privacy
- Vendor documentation pending
No dated, scoped commercial security attestation was reviewed. Data transfer, storage, deletion, access control, and incident-response terms remain to be obtained.
- Training and support
- Vendor documentation pending
The vendor describes background automation, but clinician training and referral-ownership onboarding commitments were not established.
- Monitoring and change control
- The FDA-cleared PCCP permits defined model-architecture and classification cut-off updates using prescribed data management, retraining, performance evaluation, and update procedures.
This establishes the regulatory change-control scope only. Installed model, notification of updates, local acceptance, and production monitoring remain site/vendor questions.
Current background referral workflow
IMVARIA describes ScreenDx as automatically assessing CT scans in the background to identify possible ILD cases for referral.
product family · checked 2026-09-05Current vendor workflow description; no quantified workload, outcome, or deployment guarantee is inferred.
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
- Retrospective multicenter pivotal study of 3,018 unique patients, enriched to 23% positive lung-fibrosis diagnoses, using independently recorded clinical diagnoses as reference. The baseline reports sensitivity 91.4% and specificity 95.2%; an additional 2,482-case low-prevalence dataset is separately described in the FDA summary.
Regulatory study context; no independent efficacy or referral-outcome claim.
- Reported sensitivity
- 91.4% (95% CI 89.0-93.3%) in the 3,018-case pivotal dataset
ScreenDx as submitted in K241891; CT interstitial-lung-finding classification against clinical diagnoses, 23% positive prevalence. This is distinct from development and external-publication cohorts.
- Reported specificity
- 95.2% (95% CI 94.3-96.1%) in the 3,018-case pivotal dataset
ScreenDx as submitted in K241891; CT interstitial-lung-finding classification against clinical diagnoses, 23% positive prevalence. This is distinct from development and external-publication cohorts.
No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.
ScreenDx FDA pivotal standalone evaluation
- DesignRetrospective multicenter standalone study
- Population3,018 unique patients; 694 positive lung-fibrosis diagnoses and 2,324 negatives; multiple CT manufacturers and protocols.
- Scopeexact submission
- Tested versionScreenDx in K241891; numeric build and operating cut-off not established in reviewed text
- Samplen=3018
- IndependenceIndependence not established
K241891
Reference diagnoses used clinical, radiological, laboratory and/or pathological assessments. Test patients did not overlap training; enriched prevalence limits translation to incidental-screening predictive values.
ScreenDx, an artificial intelligence-based algorithm for the incidental detection of pulmonary fibrosis
- DesignDevelopment, tuning, and external cohort validation
- PopulationDevelopment cohort 3,658 CT cases; US tuning cohort 381; separate international external-validation cohort 683.
- Scopeproduct family
- Tested versionScreenDx; exact build and equivalence to K241891 not established in the abstract
- Samplen=683
- IndependenceSponsor or vendor study
PMID:40020875 · DOI:10.1016/j.amjms.2025.02.011
Abstract and conflict disclosures reviewed through the live PubMed search result after a direct-page challenge. Imvaria funded the work and employed three authors. Metrics are not transferred to the exact-submission dossier.
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
- Vendor documentation pending
The reviewed official ScreenDx page requests contact and does not specify a scoped price. Confirm per-case or enterprise terms, integration, minimum volume, and support; procurement research is incomplete.
- Reimbursement and coding
- Research pending
No applicable payer policy was reviewed; Fibresolve or underlying CT payment cannot establish ScreenDx reimbursement.
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
No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.
Buyer worksheet
Open questions to take to the vendor
- Verify deployment and data flow: FDA describes APIs and an ingestion/analysis system but does not establish the current customer's hosting topology, region, or retention terms.
- Verify security and privacy controls: No dated, scoped commercial security attestation was reviewed. Data transfer, storage, deletion, access control, and incident-response terms remain to be obtained.
- Verify training: The vendor describes background automation, but clinician training and referral-ownership onboarding commitments were not established.
- Verify pricing and total cost: The reviewed official ScreenDx page requests contact and does not specify a scoped price. Confirm per-case or enterprise terms, integration, minimum volume, and support; procurement research is incomplete.
- Verify reimbursement and coding relevance: No applicable payer policy was reviewed; Fibresolve or underlying CT payment cannot establish ScreenDx reimbursement.
- Verify recalls and postmarket safety signals: No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.
Research record
What has been checked
This audit distinguishes completed source review from fields that have not yet been researched.
Human reviewedStatus
2026-09-05Last searched
26Fields reviewed
12Source classes checked
3Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads
Stored metadata for all three papers screened. PMID 40020875 abstract and disclosures support a product-family contextual study; exact build linkage is unresolved. PMID 37822853 and PMID 41314436 are relevant pulmonary-fibrosis/ILD leads but full methods/version linkage were not reviewed and no results were promoted. No stored trial candidates. The current discovery snapshot contains 3 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, vendor product page, literature index, peer reviewed literature, trial registry, 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
-
FDA 510(k) K241891: ScreenDx
Scope: identity, purpose, clinicalUse, modality, anatomy, input, output, limitations, integration, evidenceSummary, reportedSensitivity, reportedSpecificity, monitoring
-
Artificial Intelligence-Enabled Medical Devices
Scope: regulatoryIdentity, modalityContext
-
ScreenDx model card (K241891)
Scope: intendedUsers, careSetting, output, reportedSensitivity, reportedSpecificity, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities
-
PubMed biomedical literature index
Scope: evidenceDiscovery
-
ClinicalTrials.gov study registry
Scope: evidenceDiscovery, studyStatus
-
openFDA Device Recall API
Scope: recallDiscovery, nativeSubmissionMatching
-
ScreenDx official product and clinical-validation page
Scope: productFamilyWorkflow, implementationCapabilities, evidenceDiscovery
-
ScreenDx, an artificial intelligence-based algorithm for the incidental detection of pulmonary fibrosis
Scope: contextualEvidenceStudy
Research history
-
K241891 FDA decision
Regulatory record
510(k)
-
Source-review record updated
Research record
human reviewed
-
Reader overview source-reviewed
Editorial review
Source-reviewed editorial overlay
Alternatives
Related tools to compare
FDA-cleared K251474
Median LCS (internal name) / eyonis LCS (trade name) (1.0)
Median Technologies
eyonis LCS is a concurrent-reading aid for radiologists that detects, localizes, and characterizes 4-30 mm solid and part-solid pulmonary nodules on low-dose chest CT images for...
- Modality
- CT/CTA
- Anatomy
- Chest/Lung
- Decision
- 2026-02-06
FDA-cleared K251203
AVIEW Lung Nodule CAD
Coreline Soft Co.,Ltd
Adjunctive alert and second-reader information for radiologists interpreting non-contrast chest CT in asymptomatic populations; the cleared nodule range is 3-20 mm.
- Modality
- CT/CTA
- Anatomy
- Chest/Lung
- Decision
- 2025-12-03
FDA-cleared K250766
LungQ 4
Thirona BV
Quantitative support for thoracic CT interpretation and treatment planning, including emphysema burden, airway/lung segmentation, endobronchial valve assessment and estimated...
- Modality
- CT/CTA
- Anatomy
- Chest/Lung
- Decision
- 2025-10-02
FDA-cleared K240554
InferRead Lung CT.AI
Infervision Medical Technology Co., Ltd.
Adjunctive pulmonary nodule detection and measurement, including temporal comparison, in chest CT screening of asymptomatic adults aged at least 55 years.
- Modality
- CT/CTA
- Anatomy
- Chest/Lung
- Decision
- 2025-05-16