基于深度学习算法的腹部 CT 主动脉钙化自动分割与定量：在纵向筛查队列中的应用。

Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort.

机构信息

E3/311 Clinical Science Center, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, WI, 53792-3252, USA.

Radiology & Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA.

出版信息

Abdom Radiol (NY). 2019 Aug;44(8):2921-2928. doi: 10.1007/s00261-019-02014-2.

DOI:10.1007/s00261-019-02014-2

PMID:30976827

Abstract

OBJECTIVE

To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort.

METHODS

Using instance segmentation with convolutional neural networks (Mask R-CNN), a fully automated vascular calcification algorithm was applied to a data set of 9914 non-contrast CT scans from 9032 consecutive asymptomatic adults (mean age, 57.5 ± 7.8 years; 4467 M/5447F) undergoing colonography screening. Follow-up scans were performed in a subset of 866 individuals (mean interval, 5.4 years). Automated abdominal aortic calcium volume, mass, and Agatston score were assessed. In addition, comparison was made with a separate validated semi-automated approach in a subset of 812 cases.

RESULTS

Mean values were significantly higher in males for Agatston score (924.2 ± 2066.2 vs. 564.2 ± 1484.2, p < 0.001), aortic calcium mass (222.2 ± 526.0 mg vs. 144.5 ± 405.4 mg, p < 0.001) and volume (699.4 ± 1552.4 ml vs. 426.9 ± 1115.5 HU, p < 0.001). Overall age-specific Agatston scores increased an average of 10%/year for the entire cohort; males had a larger Agatston score increase between the ages of 40 to 60 than females (91.2% vs. 75.1%, p < 0.001) and had significantly higher mean Agatston scores between ages 50 and 80 (p < 0.001). For the 812-scan subset with both automated and semi-automated methods, median difference in Agatston score was 66.4 with an r agreement value of 0.84. Among the 866-patient cohort with longitudinal follow-up, the average Agatston score change was 524.1 ± 1317.5 (median 130.9), reflecting a mean increase of 25.5% (median 73.6%).

CONCLUSION

This robust, fully automated abdominal aortic calcification scoring tool allows for both individualized and population-based assessment. Such data could be automatically derived at non-contrast abdominal CT, regardless of the study indication, allowing for opportunistic assessment of cardiovascular risk.

摘要

目的

在成人筛查队列中，研究一种用于腹部 CT 的自动主动脉钙分段和评分工具。

方法

使用基于实例的卷积神经网络（Mask R-CNN）进行分割，将一种全自动血管钙化算法应用于 9032 例连续无症状成年人（平均年龄 57.5±7.8 岁；4467 例男性/5447 例女性）的 9914 例非对比 CT 扫描数据集中。在 866 名患者的亚组中进行了随访扫描（平均间隔时间为 5.4 年）。评估自动腹主动脉钙体积、质量和 Agatston 评分。此外，还在 812 例患者的亚组中与单独验证的半自动方法进行了比较。

结果

男性的 Agatston 评分（924.2±2066.2 比 564.2±1484.2，p<0.001）、主动脉钙质量（222.2±526.0 比 144.5±405.4 比，p<0.001）和体积（699.4±1552.4 比 426.9±1115.5 HU，p<0.001）的平均值均显著较高。整个队列的年龄特异性 Agatston 评分平均每年增加 10%；40 至 60 岁之间的男性比女性的 Agatston 评分增加更大（91.2%比 75.1%，p<0.001），50 至 80 岁之间的男性平均 Agatston 评分显著更高（p<0.001）。对于具有自动和半自动方法的 812 例扫描亚组，Agatston 评分的中位数差异为 66.4，r 一致性值为 0.84。在具有纵向随访的 866 例患者队列中，Agatston 评分的平均变化为 524.1±1317.5（中位数为 130.9），反映出平均增加 25.5%（中位数为 73.6%）。