文献速递心血管CT

从冠状动脉CT血管成像中识别和量化心血管结构:一种端到端、快速、像素级深度学习方法

Identification and Quantification of Cardiovascular Structures From CCTA: An End-to-End, Rapid, Pixel-Wise, Deep-Learning Method.
PubMed 文献 · JACC Cardiovasc Imaging · 2019-10-11

本研究设计并评估了一种用于心脏分割和量化的端到端深度学习方案,基于166例多中心临床CCTA扫描,以手动标注作为参考标准,在70:20:10拆分下训练、验证和测试。模型对左心室容积、右心室容积、左心房容积、右心房容积和左心室心肌质量的像素级分割中位Dice评分为0.9246,与手动标注相关性好且一致性好,可快速分割和量化心脏结构。

要点

  • 模型对左心室容积、右心室容积、左心房容积、右心房容积和左心室心肌质量的中位Dice评分为0.915–0.938,像素级分割准确性高。
  • 模型预测与手动标注相关性好:左心室容积r=0.98、右心室容积r=0.97、左心房容积r=0.78、右心房容积r=0.97、左心室心肌质量r=0.94(P均<0.05)。
  • 左心室容积、右心室容积、左心房容积、右心房容积和左心室心肌质量的平均差分别为1.20 ml、-0.78 ml、-3.75 ml、0.97 ml和6.41 g,与手动标注一致性好。

核心结论

  • 深度学习模型能快速分割和量化心脏结构,像素级准确性高,与手动标注一致性好,有助于扩展至研究和临床相关领域。

研究设计与样本

  • 研究从多中心注册中心获取166例接受临床指征CCTA患者的扫描,以手动标注的左心室容积、右心室容积、左心房容积、右心房容积和左心室心肌质量为参考标准,训练、验证和测试按70:20:10拆分,采用U-Net启发的深度学习模型。

诊断标准与关键数值

  • 整体中位Dice评分为0.9246(四分位距0.8870–0.9475)。
  • 左心室容积、右心室容积、左心房容积、右心房容积和左心室心肌质量的中位Dice评分分别为0.938(四分位距0.887–0.958)、0.927(四分位距0.916–0.946)、0.934(四分位距0.899–0.950)、0.915(四分位距0.890–0.920)和0.920(四分位距0.811–0.944)。
  • 模型预测与手动标注的相关系数:左心室容积r=0.98、右心室容积r=0.97、左心房容积r=0.78、右心房容积r=0.97、左心室心肌质量r=0.94(P均<0.05)。
  • 平均差和一致性界限:左心室容积1.20 ml(95%CI:-7.12至9.51)、右心室容积-0.78 ml(95%CI:-10.08至8.52)、左心房容积-3.75 ml(95%CI:-21.53至14.03)、右心房容积0.97 ml(95%CI:-6.14至8.09)、左心室心肌质量6.41 g(95%CI:-8.71至21.52)。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: This study designed and evaluated an end-to-end deep learning solution for cardiac segmentation and quantification.

BACKGROUND: Segmentation of cardiac structures from coronary computed tomography angiography (CCTA) images is laborious. We designed an end-to-end deep-learning solution.

METHODS: Scans were obtained from multicenter registries of 166 patients who underwent clinically indicated CCTA. Left ventricular volume (LVV) and right ventricular volume (RVV), left atrial volume (LAV) and right atrial volume (RAV), and left ventricular myocardial mass (LVM) were manually annotated as ground truth. A U-Net-inspired, deep-learning model was trained, validated, and tested in a 70:20:10 split.

RESULTS: Mean age was 61.1 ± 8.4 years, and 49% were women. A combined overall median Dice score of 0.9246 (interquartile range: 0.8870 to 0.9475) was achieved. The median Dice scores for LVV, RVV, LAV, RAV, and LVM were 0.938 (interquartile range: 0.887 to 0.958), 0.927 (interquartile range: 0.916 to 0.946), 0.934 (interquartile range: 0.899 to 0.950), 0.915 (interquartile range: 0.890 to 0.920), and 0.920 (interquartile range: 0.811 to 0.944), respectively. Model prediction correlated and agreed well with manual annotation for LVV (r = 0.98), RVV (r = 0.97), LAV (r = 0.78), RAV (r = 0.97), and LVM (r = 0.94) (p < 0.05 for all). Mean difference and limits of agreement for LVV, RVV, LAV, RAV, and LVM were 1.20 ml (95% CI: -7.12 to 9.51), -0.78 ml (95% CI: -10.08 to 8.52), -3.75 ml (95% CI: -21.53 to 14.03), 0.97 ml (95% CI: -6.14 to 8.09), and 6.41 g (95% CI: -8.71 to 21.52), respectively.

CONCLUSIONS: A deep-learning model rapidly segmented and quantified cardiac structures. This was done with high accuracy on a pixel level, with good agreement with manual annotation, facilitating its expansion into areas of research and clinical import.

来源:JACC Cardiovasc Imaging,查看原文。版权归原作者所有。

引用

  1. Baskaran L, Maliakal G, Al'Aref SJ, et al. Identification and Quantification of Cardiovascular Structures From CCTA: An End-to-End, Rapid, Pixel-Wise, Deep-Learning Method. JACC Cardiovasc Imaging. 2019. PMID: 31607673. doi:10.1016/j.jcmg.2019.08.025

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。