Automatic detection and quantification of the Agatston coronary artery calcium score on contrast computed tomography angiography

Abstract

Potentially, Agatston coronary artery calcium (CAC) score could be calculated on contrast computed tomography coronary angiography (CTA). This will make a separate non-contrast CT scan superfluous. This study aims to assess the performance of a novel fully automatic algorithm to detect and quantify the Agatston CAC score in contrast CTA images. From a clinical registry, 20 patients were randomly selected for each CAC category (i.e. 0, 1-99, 100-399, 400-999, ≥1,000). The Agatston CAC score on non-contrast CT was calculated manually, while the novel algorithm was used to automatically detect and quantify Agatston CAC score in contrast CTA images. The resulting Agatston CAC scores were validated against the non-contrast images. A total of 100 patients (60 ± 11 years, 63 men) were included. The median CAC score on non-contrast CT was 145 (IQR 5-760), whereas the contrast CTA CAC score was 170 (IQR 23-594) (P = 0.004). The automatically computed CAC score showed a high correlation (R = 0.949; P < 0.001) and intra-class correlation (R = 0.863; P < 0.001) with non-contrast CT CAC score. Moreover, agreement within CAC categories was good (κ 0.588). Fully automatic detection of Agatston CAC score on contrast CTA is feasible and showed high correlation with non-contrast CT CAC score. This could imply a radiation dose reduction and time saving by omitting the non-contrast scan.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework

“…First, methods have been evaluated using different data sets, in terms of image acquisition, image reconstruction, and patient inclusion. CAC scoring methods have been developed for diverse CT images of the heart, namely, CSCT, 10,11,[16][17][18]20,21,23 contrast-enhanced coronary CT angiography (CCTA), 9,12,14,19,24,25 a combination of CSCT and CCTA (Ref. 22), or noncontrast-enhanced non-ECG-triggered chest CT. 13,26 These scans may all be used to determine the amount of CAC, but their characteristics pose different challenges.…”

“…The number of included patients per study ranged from 10 to 530, including lung cancer screening participants 26 and patients with known or suspected CVD. 12 Hence, anatomical characteristics and CAC distribution might differ across studies. Second, the CAC scoring task was described and evaluated differently across studies.…”

Automatic coronary calcium scoring using noncontrast and contrast CT images

“…Besides the methods mentioned above, several algorithms 18,19 have been developed recently to detect coronary calcifications and compute calcium scoring only using the contrast cardiac CT images. However, the clinical value of deriving the calcium scores from only contrast CT images still needs to be studied.…”

Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions

“…Automatic scoring methods therefore typically perform a segmentation of the coronary artery tree. The segmentation is used to detect calcifications by searching for strong intensity gradients along the segmented vessel [16]- [19] because calcifications are typically brighter than the contrast enhanced lumen of the vessel. In a similar approach, Mittal et al [20] employ a classifier to detect calcifications based on features that describe the texture along the vessel.…”