文献速递心血管MR

基于深度学习的全自动心内4D血流MRI后处理用于双心室分割

Fully automated intracardiac 4D flow MRI post-processing using deep learning for biventricular segmentation.
PubMed 文献 · Eur Radiol · 2022-02-17

本研究评估基于深度学习的左、右心室自动分割在短轴cine bSSFP图像上的表现,并在106例本地数据库微调后于26例测试者中与3名人工观察者比较。自动分割的Dice分数与人工分割相近,左心室平均动能和右心室动能的相对偏差低于人工观察者间偏差,提示该方法可减少后处理时间并降低观察者间变异。

要点

  • 自动分割Dice分数左心室0.92、右心室0.86,与人工分割相近。
  • 左心室平均动能自动与人工偏差8%,低于人工观察者间11%(p=0.01)。
  • 右心室动能自动与人工偏差15%,低于人工观察者间19%(p=0.03)。

核心结论

  • 基于深度学习的全自动后处理方法所得血流动力学测量与人工观察者测量的差异等于或小于人工观察者间的变异,可用于减少心室内4D血流数据后处理时间并减轻观察者间变异。

研究设计与样本

  • 研究论文;在106例本机构扫描受试者组成的本地数据库上对既往发表的深度学习网络进行微调,在26例测试受试者中于bSSFP MRI上由网络自动分割心室并由3名人工观察者手动分割,再将bSSFP图像配准至相应4D血流图像以将分割应用于4D血流速度数据,评估Dice系数及多种血流动力学参数测量的相对偏差(自动vs人工、人工观察者间)。

诊断标准与关键数值

  • 自动分割Dice分数:左心室0.92,右心室0.86。
  • 人工分割观察者间Dice分数:左心室0.91,右心室0.87。
  • 左心室平均动能自动分割与人工分割相对偏差8%,人工观察者间相对偏差11%(p=0.01)。
  • 右心室动能自动分割与人工分割相对偏差15%,人工观察者间相对偏差19%(p=0.03)。

临床应用与阅片要点

  • 作者认为该方法可用于减少心室内4D血流数据后处理时间并减轻观察者间变异。
  • 作者指出自动后处理所得血流动力学测量与人工观察者测量的差异等于或小于人工观察者间变异。

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: 4D flow MRI allows for a comprehensive assessment of intracardiac blood flow, useful for assessing cardiovascular diseases, but post-processing requires time-consuming ventricular segmentation throughout the cardiac cycle and is prone to subjective errors. Here, we evaluate the use of automatic left and right ventricular (LV and RV) segmentation based on deep learning (DL) network that operates on short-axis cine bSSFP images.

METHODS: A previously published DL network was fine-tuned via retraining on a local database of 106 subjects scanned at our institution. In 26 test subjects, the ventricles were segmented automatically by the network and manually by 3 human observers on bSSFP MRI. The bSSFP images were then registered to the corresponding 4D flow images to apply the segmentation to 4D flow velocity data. Dice coefficients and the relative deviation between measurements (automatic vs. manual and interobserver manual) of various hemodynamic parameters were assessed.

RESULTS: The automated segmentation resulted in similar Dice scores (LV: 0.92, RV: 0.86) and lower relative deviations from manual segmentation in left ventricular (LV) average kinetic energy (KE) (8%) and RV KE (15%) than the Dice scores (LV: 0.91, RV: 0.87) and relative deviations between manual segmentation observers (LV KE: 11%, p = 0.01; RV KE: 19%, p = 0.03).

CONCLUSIONS: The automated post-processing method using deep learning resulted in hemodynamic measurements that differ from a manual observer's measurements equally or less than the variation between manual observers. This approach can be used to decrease post-processing time on intraventricular 4D flow data and mitigate interobserver variability.

KEY POINTS: • Our proposed method allows for fully automated post-processing of intraventricular 4D flow MRI data. • Our method resulted in hemodynamic measurements that matched those derived from manual segmentation equally as well as interobserver variability. • Our method can be used to greatly accelerate intraventricular 4D flow post-processing and improve interobserver repeatability.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Corrado, Wentland, Starekova, et al. Fully automated intracardiac 4D flow MRI post-processing using deep learning for biventricular segmentation. Eur Radiol. 2022. PMID: 35175379. doi:10.1007/s00330-022-08616-7

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。