文献速递心血管MR

以时间作为第三维度可靠分割二维心脏磁共振灌注图像序列

Reliable segmentation of 2D cardiac magnetic resonance perfusion image sequences using time as the 3rd dimension.
PubMed 文献 · Eur Radiol · 2020-11-27

本研究比较了不同深度学习方法用于心脏磁共振首过灌注图像心肌分割,评估二维和三维(二维加时间)U-Net 及运动校正的作用,并提出一种带新型时间池化层的改进 U-Net。最佳 DICE 分数为左心室心肌 0.86、左心室腔 0.90,最佳 Hausdorff 距离分别为 2.3 和 2.1 像素;在第二个独立测试集 20 例患者中表现相似(左心室心肌最佳 DICE 0.84)。结论认为运动校正联合三维卷积网络的分割效果最佳,显著优于所有测试的二维方法。

要点

  • 运动校正联合三维(二维加时间)卷积网络对左心室心肌分割效果最佳,显著优于所有测试的二维方法。
  • 最佳 DICE 分数为左心室心肌 0.86、左心室腔 0.90,最佳 Hausdorff 距离分别为 2.3 和 2.1 像素(5 折交叉验证)。
  • 在第二个独立测试集 20 例患者中左心室心肌最佳 DICE 为 0.84,表现相似。

关键影像表现/征象

  • 心脏磁共振首过灌注序列提供心脏动态对比增强的二维图像时间序列。
  • 准确的灌注图像心肌分割对定量分析至关重要,并有助于实现自动的像素级心肌灌注定量。

诊断标准与关键数值

  • 最佳 DICE 分数:左心室心肌 0.86、左心室腔 0.90(5 折交叉验证)。
  • 最佳 Hausdorff 距离:左心室心肌 2.3 像素、左心室腔 2.1 像素(5 折交叉验证)。
  • 第二个独立测试集 20 例患者中,左心室心肌最佳 DICE 分数为 0.84,表现相似。

临床应用与阅片要点

  • 可靠的逐帧心肌分割有助于像素级灌注评估。
  • 深度学习联合运动校正、三维(二维加时间)方法和深度时间连接模块可产生可靠的分割结果。

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: Cardiac magnetic resonance (CMR) first-pass perfusion is an established noninvasive diagnostic imaging modality for detecting myocardial ischemia. A CMR perfusion sequence provides a time series of 2D images for dynamic contrast enhancement of the heart. Accurate myocardial segmentation of the perfusion images is essential for quantitative analysis and it can facilitate automated pixel-wise myocardial perfusion quantification.

METHODS: In this study, we compared different deep learning methodologies for CMR perfusion image segmentation. We evaluated the performance of several image segmentation methods using convolutional neural networks, such as the U-Net in 2D and 3D (2D plus time) implementations, with and without additional motion correction image processing step. We also present a modified U-Net architecture with a novel type of temporal pooling layer which results in improved performance.

RESULTS: The best DICE scores were 0.86 and 0.90 for LV myocardium and LV cavity, while the best Hausdorff distances were 2.3 and 2.1 pixels for LV myocardium and LV cavity using 5-fold cross-validation. The methods were corroborated in a second independent test set of 20 patients with similar performance (best DICE scores 0.84 for LV myocardium).

CONCLUSIONS: Our results showed that the LV myocardial segmentation of CMR perfusion images is best performed using a combination of motion correction and 3D convolutional networks which significantly outperformed all tested 2D approaches. Reliable frame-by-frame segmentation will facilitate new and improved quantification methods for CMR perfusion imaging.

KEY POINTS: • Reliable segmentation of the myocardium offers the potential to perform pixel level perfusion assessment. • A deep learning approach in combination with motion correction, 3D (2D + time) methods, and a deep temporal connection module produced reliable segmentation results.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Sandfort V, Jacobs M, Arai AE, et al. Reliable segmentation of 2D cardiac magnetic resonance perfusion image sequences using time as the 3rd dimension. Eur Radiol. 2020. PMID: 33247342. doi:10.1007/s00330-020-07474-5

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。