文献速递心血管MR

深度学习语义分割全自动MRI左心室形变分析在心心脏毒性中的验证

Validation of a deep-learning semantic segmentation approach to fully automate MRI-based left-ventricular deformation analysis in cardiotoxicity.
PubMed 文献 · Br J Radiol · 2021-02-24

本研究用DeepLabV3+深度卷积神经网络(三种ResNet-50骨干)对42例女性乳腺癌DENSE MRI数据集进行左心室腔量化,并与厂商工具比较。改良ResNet-50心肌分割准确度97%、Dice 0.92、APD 1.2 mm;LVEF的Cronbach's α=0.97(三组均约54–55%,p=0.6),LVEDD的C-Alpha=0.87(三组均4.6 cm,p=0.7)。作者认为改良空洞网络可用于自动化左心室腔量化及后续应变分析。

要点

  • 改良ResNet-50分割DENSE图像心肌准确度97%、Dice 0.92、APD 1.2 mm。
  • 改良与空洞ResNet-50及厂商工具间LVEF的C-Alpha=0.97、LVEDD的C-Alpha=0.87。
  • 三组LVEF(约54–55%,p=0.6)和LVEDD(4.6 cm,p=0.7)无显著差异。

关键影像表现/征象

  • 改良ResNet-50心肌分类准确度97%、Dice 0.92、APD 1.2 mm。
  • 空洞ResNet-50心肌分类准确度95%、Dice 0.90、APD 1.7 mm。

诊断标准与关键数值

  • 改良ResNet-50、空洞ResNet-50与厂商工具间LVEF的C-Alpha=0.97(55±7%、54±7%、54±7%,p=0.6)。
  • 改良ResNet-50、空洞ResNet-50与厂商工具间LVEDD的C-Alpha=0.87(4.6±0.3 cm、4.6±0.3 cm、4.6±0.4 cm,p=0.7)。
  • 心肌分类验证指标包括准确度、Dice和平均垂直距离(APD)。

临床应用与阅片要点

  • 作者认为改良空洞DCNN分割可用于心脏毒性检测中的自动化左心室腔量化及后续应变分析。
  • LVEF、LVEDD在改良网络、空洞网络与厂商工具间无显著差异(p=0.6、p=0.7)。

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

OBJECTIVE: Left-ventricular (LV) strain measurements with the Displacement Encoding with Stimulated Echoes (DENSE) MRI sequence provide accurate estimates of cardiotoxicity damage related to chemotherapy for breast cancer. This study investigated an automated and supervised deep convolutional neural network (DCNN) model for LV chamber quantification before strain analysis in DENSE images.

METHODS: The DeepLabV3 +DCNN with three versions of ResNet-50 backbone was designed to conduct chamber quantification on 42 female breast cancer data sets. The convolutional layers in the three ResNet-50 backbones were varied as non-atrous, atrous and modified, atrous with accuracy improvements like using Laplacian of Gaussian filters. Parameters such as LV end-diastolic diameter (LVEDD) and ejection fraction (LVEF) were quantified, and myocardial strains analyzed with the Radial Point Interpolation Method (RPIM). Myocardial classification was validated with the performance metrics of accuracy, Dice, average perpendicular distance (APD) and others. Repeated measures ANOVA and intraclass correlation (ICC) with Cronbach's α (C-Alpha) tests were conducted between the three DCNNs and a vendor tool on chamber quantification and myocardial strain analysis.

RESULTS: Validation results in the same test-set for myocardial classification were accuracy = 97%, Dice = 0.92, APD = 1.2 mm with the modified ResNet-50, and accuracy = 95%, Dice = 0.90, APD = 1.7 mm with the atrous ResNet-50. The ICC results between the modified ResNet-50, atrous ResNet-50 and vendor-tool were C-Alpha = 0.97 for LVEF (55±7%, 54±7%, 54±7%, p = 0.6), and C-Alpha = 0.87 for LVEDD (4.6 ± 0.3 cm, 4.6 ± 0.3 cm, 4.6 ± 0.4 cm, p = 0.7).

CONCLUSION: Similar performance metrics and equivalent parameters obtained from comparisons between the atrous networks and vendor tool show that segmentation with the modified, atrous DCNN is applicable for automated LV chamber quantification and subsequent strain analysis in cardiotoxicity.

ADVANCES IN KNOWLEDGE: A novel deep-learning technique for segmenting DENSE images was developed and validated for LV chamber quantification and strain analysis in cardiotoxicity detection.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Karr J, Cohen M, McQuiston SA, et al. Validation of a deep-learning semantic segmentation approach to fully automate MRI-based left-ventricular deformation analysis in cardiotoxicity. Br J Radiol. 2021. PMID: 33571002. doi:10.1259/bjr.20201101

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。