Simultaneous assessment of heart and lungs with gated high-pitch ultra-low dose chest CT using artificial intelligence-based calcium scoring

Performance assessment of an artificial intelligence-based coronary artery calcium scoring algorithm in non-gated chest CT scans of different slice thickness

Background

The coronary artery calcium score (CACS) has been shown to be an independent predictor of cardiovascular events. The traditional coronary artery calcium scoring algorithm has been optimized for electrocardiogram (ECG)-gated images, which are acquired with specific settings and timing. Therefore, if the artificial intelligence-based coronary artery calcium score (AI-CACS) could be calculated from a chest low-dose computed tomography (LDCT) examination, it could be valuable in assessing the risk of coronary artery disease (CAD) in advance, and it could potentially reduce the occurrence of cardiovascular events in patients. This study aimed to assess the performance of an AI-CACS algorithm in non-gated chest scans with three different slice thicknesses (1, 3, and 5 mm).

Methods

A total of 135 patients who underwent both LDCT of the chest and ECG-gated non-contrast enhanced cardiac CT were prospectively included in this study. The Agatston scores were automatically derived from chest CT images reconstructed at slice thicknesses of 1, 3, and 5 mm using the AI-CACS software. These scores were then compared to those obtained from the ECG-gated cardiac CT data using a conventional semi-automatic method that served as the reference. The correlations between the AI-CACS and electrocardiogram-gated coronary artery calcium score (ECG-CACS) were analyzed, and Bland-Altman plots were used to assess agreement. Risk stratification was based on the calculated CACS, and the concordance rate was determined.

Results

A total of 112 patients were included in the final analysis. The correlations between the AI-CACS at three different thicknesses (1, 3, and 5 mm) and the ECG-CACS were 0.973, 0.941, and 0.834 (all P<0.01), respectively. The Bland-Altman plots showed mean differences in the AI-CACS for the three thicknesses of -6.5, 15.4, and 53.1, respectively. The risk category agreement for the three AI-CACS groups was 0.868, 0.772, and 0.412 (all P<0.01), respectively. While the concordance rates were 91%, 84.8%, and 62.5%, respectively.

Conclusions

The AI-based algorithm successfully calculated the CACS from LDCT scans of the chest, demonstrating its utility in risk categorization. Furthermore, the CACS derived from images with a slice thickness of 1 mm was more accurate than those obtained from images with slice thicknesses of 3 and 5 mm.

Coronary artery calcium scoring assessment in ultra-low-dose chest computed tomography

OBJECTIVES

To investigate the effect of non-electrocardiogram (ECG) -triggered ultra-low-dose CT (ULD-CT) with different reconstruction protocols on coronary artery calcium (CAC) scoring assessment, compared with ECG-triggered CAC CT (CAC-CT).

METHODS

This prospective study included 115 patients who underwent CAC-CT and ULD-CT scans under the same topogram images. CAC-CT adopted a prospective ECG-triggered sequential acquisition with a tube potential of 120 kV, and the reconstruction protocol was standard Qr36 + slice 3 mm (CACQr-3mm group). ULD-CT adopted a non-ECG-triggered high-pitch acquisition with a tube potential of Sn100 kV, and four groups of images (named ULDQr-3mm, ULDSa-3mm, ULDQr-1.5mm, and ULDSa-1.5mm) were reconstructed using different reconstruction algorithms (standard Qr36, kV-independent Sa36) and slice thicknesses (3 mm, 1.5 mm). The accuracy of CAC detection by ULD-CT was calculated. The agreement of the CAC score between ULD-CT and CAC-CT scans was assessed using intraclass correlation coefficients (ICC) and Bland-Altman plot, and the agreement of risk categorization was assessed using weighted kappa.

RESULTS

The sensitivity and specificity of the ULDSa-1.5mm group for detecting positive CAC were 100% and 97.4%, respectively (k = 0.980). The CAC score for the ULDSa-3mm and ULDSa-1.5mm groups demonstrated excellent agreement with the CACQr-3mm group (ICC = 0.992, 0.990, respectively), with a mean difference of -12.3 and - 12.4. The agreement of risk categorization based on absolute and percentile CAC score between the ULDSa-1.5mm and CACQr-3mm groups was excellent (weighted k = 0.954, 0.983, respectively), and risk reclassification rates were low (3.5%, 2.8%, respectively). The effective dose was reduced by approximately 77.2% for the ULD-CT compared to the CAC-CT (0.18 mSv vs. 0.79 mSv, p < 0.001).

CONCLUSION

Reconstruction with a 1.5-mm slice thickness and kV-independent iterative algorithmic protocol in ULD-CT yielded excellent agreement in CAC score quantification and risk categorization compared with ECG-triggered CAC-CT.