Related Experiment Video
Updated: Sep 12, 2025
Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans
Published on: August 28, 2018
Vessel-specific reliability of artificial intelligence-based coronary artery calcium scoring on non-ECG-gated chest
Jing Zhang1, Kefu Liu1, Chenyang You2
1Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, China.
Insights
Artificial intelligence (AI) coronary artery calcium scoring (CACS) on non-electrocardiogram (ECG)-gated chest CT shows promise for opportunistic screening. However, significant risk misclassification rates necessitate protocol optimization for improved accuracy, especially for specific coronary arteries.
Area of Science:
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
- Radiology
Background:
- Coronary artery calcium scoring (CACS) is crucial for cardiovascular risk assessment.
- Electrocardiogram (ECG)-gated cardiac CT is the standard for accurate CACS.
- Non-ECG-gated chest CT offers potential for opportunistic CACS assessment.
Purpose of the Study:
- To evaluate the performance of AI-based CACS on non-ECG-gated chest CT.
- To compare AI CACS with manual quantification (reference standard).
- To assess per-vessel reliability and impact on clinical risk classification.
Main Methods:
- Retrospective analysis of 290 patients with paired non-ECG-gated chest CT and ECG-gated cardiac CT.
- Comparison of AI-based CACS and manual CACS (CACS_man) using intraclass correlation coefficient (ICC) and Cohen's kappa.
- Assessment of error types and anatomical distributions per Society of Cardiovascular Computed Tomography (SCCT) guidelines.
Main Results:
- Excellent overall concordance between AI CACS on chest CT and CACS_man (ICC = 0.87).
- Non-ECG-gated chest CT showed a 7.5-fold higher risk misclassification rate (41.4%) compared to ECG-gated CT (5.5%).
- Vessel-specific analysis revealed variable reliability, with suboptimal performance for the right coronary artery (RCA) and issues with stent misclassification in the left anterior descending artery (LAD).
Conclusions:
- AI-based CACS on non-ECG-gated chest CT is useful for opportunistic screening.
- Protocol optimization is needed to address vessel-specific limitations and reduce misclassification rates.
- Mitigating the substantial risk misclassification (41.4%) is critical for clinical utility.
Purpose:
To evaluate the performance of artificial intelligence (AI)-based coronary artery calcium scoring (CACS) on non-electrocardiogram (ECG)-gated chest CT, using manual quantification as the reference standard, while characterizing per-vessel reliability and clinical risk classification impacts.
Methods:
Retrospective study of 290 patients (June 2023-2024) with paired non-ECG-gated chest CT and ECG-gated cardiac CT (median time was 2 days). AI-based CACS and manual CACS (CACS_man) were compared using intraclass correlation coefficient (ICC) and weighted Cohen's kappa (3,1). Error types, anatomical distributions, and CACS of the lesions of individual arteries or segments were assessed in accordance with the Society of Cardiovascular Computed Tomography (SCCT) guidelines.
Results:
The total CACS of chest CT demonstrated excellent concordance with CACS_man (ICC = 0.87, 95 % CI 0.84-0.90). Non-ECG-gated chest showed a 7.5-fold increased risk misclassification rate compared to ECG-gated cardiac CT (41.4 % vs. 5.5 %), with 35.5 % overclassification and 5.9 % underclassification. Vessel-specific analysis revealed paradoxical reliability of the left anterior descending artery (LAD) due to stent misclassification in four cases (ICC = 0.93 on chest CT vs 0.82 on cardiac CT), while the right coronary artery (RCA) demonstrated suboptimal performance with ICCs ranging from 0.60 to 0.68. Chest CT exhibited higher false-positive (1.9 % vs 0.5 %) and false-negative rates (14.4 % vs 4.3 %). False positive mainly derived from image noise in proximal LAD/RCA (median CACS 5.97 vs 3.45) and anatomical error, while false negatives involved RCA microcalcifications (median CACS 2.64).
Conclusions:
AI-based non-ECG-gated chest CT demonstrates utility for opportunistic screening but requires protocol optimization to address vessel-specific limitations and mitigate 41.4 % risk misclassification rates.
More Related Videos
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:28Imaging Studies for Cardiovascular System V: CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:21Imaging Studies for Cardiovascular System IV: CMRI
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:17Imaging Studies for Cardiovascular System I:Echocardiography
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion,...