Deep-learning screening for coronary artery disease on routine chest CT

Deep Learning-Based Opportunistic Screening of Coronary Artery Disease on Non-Contrast Chest CT: A Multicenter Study

Observational Zhejiang Chinese Medical University · NCT07181512

This project will test whether deep learning can find coronary artery calcification on routine non-contrast chest CT in adults who also had coronary CT angiography.

Quick facts

Study typeObservational
Enrollment200 (estimated)
Ages18 Years and up
SexAll
SponsorZhejiang Chinese Medical University Government
Drugs / interventionsradiation
Locations2 sites (Hangzhou, Zhejiang and 1 other locations)
Trial IDNCT07181512 on ClinicalTrials.gov

What this trial studies

This multicenter, retrospective analysis uses de-identified imaging from adults who underwent both non-contrast chest CT and coronary CT angiography (CCTA) within 30 days. Deep-learning models will be developed and validated to analyze calcified coronary segments visible on non-contrast chest CT, using CCTA as the reference standard. No additional imaging, radiation, or interventions are performed and the institutional review board approved a waiver of written consent. Segments with motion or metal artifacts, stents, or completely obscured lumens will be excluded and models will be tested across participating hospitals to assess generalizability.

Who should consider this trial

Good fit: Ideal candidates are adults (≥18) who had both non-contrast chest CT and CCTA within 30 days with coronary segments clearly visible on the non-contrast scan.

Not a fit: Patients with motion or metal artifacts, coronary stents, completely obscured vessel lumens, or without matched CCTA within 30 days are unlikely to benefit.

Why it matters

Potential benefit: If successful, this could enable low-cost, opportunistic screening for coronary artery disease using existing chest CT scans and help identify high-risk people earlier.

How similar studies have performed: Prior research using calcium scoring and machine learning on non-contrast chest CT has shown promising results, but multicenter validation remains limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Age ≥18 years
2. Patients who underwent both non-contrast chest CT and coronary CT angiography (CCTA) within 30 days
3. Coronary segments clearly visualized on non-contrast chest CT

Exclusion Criteria:

1. Segments with motion artifacts, metal artifacts, or stents preventing analysis
2. Vessel lumen completely obscured by calcification (unrecognizable vascular course)
3. Inability to match coronary segment location between non-contrast chest CT and CCTA

Where this trial is running

Hangzhou, Zhejiang and 1 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Coronary Artery DiseaseCoronary Artery Stenosis StentNon-contrast Chest CTCoronary CT AngiographyOpportunistic ScreeningArtificial Intelligence
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.