文献速递心血管MR

基于深度学习的方法从电影MR图像全自动定量左心室功能:多厂商、多中心研究

Deep Learning-based Method for Fully Automatic Quantification of Left Ventricle Function from Cine MR Images: A Multivendor, Multicenter Study.
PubMed 文献 · Radiology · 2018-10-09

本回顾性研究纳入2008至2016年四个医学中心、三家主要MRI厂商的电影MRI数据集,训练三个U-NET架构卷积神经网络(CNN1单厂商单中心100例,CNN2单厂商多中心200例,CNN3多厂商多中心400例),并在独立多厂商多中心196例数据集上测试。CNN3表现最佳,其与手动分析的平均垂直距离为1.1 mm ± 0.3,低于CNN1的1.5 mm ± 1.0(P < .05)和CNN2的1.3 mm ± 0.6(P < .05);CNN3导出的左心室功能参数与专家结果高度相关(r2 ≥ 0.98)且一致。

要点

  • CNN3在独立多厂商多中心测试集上表现最佳,左心室功能参数与专家手动结果高度相关(r2 ≥ 0.98)。
  • CNN3与手动分析的平均垂直距离为1.1 mm ± 0.3,低于CNN1的1.5 mm ± 1.0和CNN2的1.3 mm ± 0.6(均P < .05)。
  • 基于高变异性数据集训练的深度学习方法可实现多厂商多中心电影MRI的全自动准确分析。

核心结论

  • 基于高变异性数据集训练的深度学习方法能在多厂商、多中心电影MRI数据上实现全自动且准确的左心室功能分析。

研究设计与样本

  • 回顾性研究,纳入2008至2016年四个医学中心、三家主要MRI厂商的电影MRI数据集;训练三个U-NET架构卷积神经网络(CNN1单厂商单中心100例、CNN2单厂商多中心200例、CNN3多厂商多中心400例),并在独立多厂商多中心196例数据集上测试,以三位经验观察者的手动标注为参考标准。

诊断标准与关键数值

  • CNN3与手动分析的平均垂直距离为1.1 mm ± 0.3,CNN1为1.5 mm ± 1.0(与CNN3比较P < .05),CNN2为1.3 mm ± 0.6(与CNN3比较P < .05)。
  • CNN3导出的左心室功能参数与专家结果高度相关(r2 ≥ 0.98)且一致,适用于不同厂商和中心的数据集。

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

Purpose To develop a deep learning-based method for fully automated quantification of left ventricular (LV) function from short-axis cine MR images and to evaluate its performance in a multivendor and multicenter setting. Materials and Methods This retrospective study included cine MRI data sets obtained from three major MRI vendors in four medical centers from 2008 to 2016. Three convolutional neural networks (CNNs) with the U-NET architecture were trained on data sets of increasing variability: (a) a single-vendor, single-center, homogeneous cohort of 100 patients (CNN1); (b) a single-vendor, multicenter, heterogeneous cohort of 200 patients (CNN2); and (c) a multivendor, multicenter, heterogeneous cohort of 400 patients (CNN3). All CNNs were tested on an independent multivendor, multicenter data set of 196 patients. CNN performance was evaluated with respect to the manual annotations from three experienced observers in terms of (a) LV detection accuracy, (b) LV segmentation accuracy, and (c) LV functional parameter accuracy. Automatic and manual results were compared with the paired Wilcoxon test, Pearson correlation, and Bland-Altman analysis. Results CNN3 achieved the highest performance on the independent testing data set. The average perpendicular distance compared with manual analysis was 1.1 mm ± 0.3 for CNN3, compared with 1.5 mm ± 1.0 for CNN1 (P < .05) and 1.3 mm ± 0.6 for CNN2 (P < .05). The LV function parameters derived from CNN3 showed a high correlation (r2 ≥ 0.98) and agreement with those obtained by experts for data sets from different vendors and centers. Conclusion A deep learning-based method trained on a data set with high variability can achieve fully automated and accurate cine MRI analysis on multivendor, multicenter cine MRI data. © RSNA, 2018 See also the editorial by Colletti in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Tao Q, Yan W, Wang Y, et al. Deep Learning-based Method for Fully Automatic Quantification of Left Ventricle Function from Cine MR Images: A Multivendor, Multicenter Study. Radiology. 2018. PMID: 30299231. doi:10.1148/radiol.2018180513

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。