Background

Separate noncontrast CT to quantify the coronary artery calcium (CAC) score often precedes coronary CT angiography (CTA). Quantifying CAC scores directly at CTA would eliminate the additional radiation produced at CT but remains challenging.

Purpose

To quantify CAC scores automatically from a single CTA scan.

Materials and Methods

In this retrospective study, a deep learning method to quantify CAC scores automatically from a single CTA scan was developed on training and validation sets of 292 patients and 73 patients collected from March 2019 to July 2020. Virtual noncontrast scans obtained with a spectral CT scanner were used to develop the algorithm to alleviate tedious manual annotation of calcium regions. The proposed method was validated on an independent test set of 240 CTA scans collected from three different CT scanners from August 2020 to November 2020 using the Pearson correlation coefficient, the coefficient of determination, or r², and the Bland-Altman plot against the semiautomatic Agatston score at noncontrast CT. The cardiovascular risk categorization performance was evaluated using weighted κ based on the Agatston score (CAC score risk categories: 0–10, 11–100, 101–400, and >400).

Results

Two hundred forty patients (mean age, 60 years ± 11 [standard deviation]; 146 men) were evaluated. The positive correlation between the automatic deep learning CTA and semiautomatic noncontrast CT CAC score was excellent (Pearson correlation = 0.96; r² = 0.92). The risk categorization agreement based on deep learning CTA and noncontrast CT CAC scores was excellent (weighted κ = 0.94 [95% CI: 0.91, 0.97]), with 223 of 240 scans (93%) categorized correctly. All patients who were miscategorized were in the direct neighboring risk groups. The proposed method’s differences from the noncontrast CT CAC score were not statistically significant with regard to scanner (P = .15), sex (P = .051), and section thickness (P = .67).

Conclusion

A deep learning automatic calcium scoring method accurately quantified coronary artery calcium from CT angiography images and categorized risk.

© RSNA, 2021

See also the editorial by Goldfarb and Cao et al in this issue.

中文翻译：

---

使用深度学习进行冠状动脉 CT 血管造影的钙评分

背景

单独的非对比 CT 量化冠状动脉钙 (CAC) 评分通常先于冠状动脉 CT 血管造影 (CTA)。直接在 CTA 量化 CAC 分数将消除 CT 产生的额外辐射，但仍然具有挑战性。

目的

从单个 CTA 扫描中自动量化 CAC 分数。

材料和方法

在这项回顾性研究中，在 2019 年 3 月至 2020 年 7 月期间收集的 292 名患者和 73 名患者的训练和验证集上开发了一种从单次 CTA 扫描中自动量化 CAC 评分的深度学习方法。使用光谱 CT 扫描仪获得的虚拟非对比扫描是用于开发算法以减轻钙区域的繁琐手动注释。使用 Pearson 相关系数、确定系数或r ^{2在 2020 年 8 月至 2020 年 11 月期间从三台不同 CT 扫描仪收集的 240 次 CTA 扫描的独立测试集上验证了所提出的方法}，以及 Bland-Altman 图与非增强 CT 上的半自动 Agatston 评分对比。使用基于 Agatston 评分的加权 κ 评估心血管风险分类性能（CAC 评分风险类别：0-10、11-100、101-400 和 >400）。

结果

对 240 名患者（平均年龄，60 岁 ± 11 [标准差]；146 名男性）进行了评估。自动深度学习 CTA 和半自动非对比 CT CAC 评分之间的正相关性非常好（Pearson 相关性 = 0.96；r ² = 0.92）。基于深度学习 CTA 和非对比 CT CAC 评分的风险分类协议非常好（加权 κ = 0.94 [95% CI：0.91, 0.97]），240 次扫描中有 223 次（93%）分类正确。所有被错误分类的患者都属于直接相邻的风险组。在扫描仪 ( P = .15)、性别 ( P = .051) 和切片厚度 ( P = .67)方面，所提出的方法与非增强 CT CAC 评分的差异没有统计学意义。

结论

深度学习自动钙评分方法从 CT 血管造影图像中准确量化冠状动脉钙并分类风险。

© 北美放射学会，2021

另见 Goldfarb 和 Cao 等人在本期的社论。