文献速递心血管MR

三维深度卷积神经网络用于肥厚型心肌病心肌瘢痕自动定量:多中心多厂商研究

Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study.
PubMed 文献 · Radiology · 2019-11-12

该多中心多厂商回顾性研究纳入1073例肥厚型心肌病患者,开发基于U-Net的三维卷积神经网络自动定量心脏MRI延迟强化瘢痕体积。三维卷积神经网络与人工定量瘢痕体积和瘢痕体积占左心室心肌总体积比例均呈优良相关,识别大瘢痕负荷(>15%)准确率达98%,分割性能优于二维卷积神经网络且在不同厂商间表现相当。

要点

  • 三维卷积神经网络自动定量肥厚型心肌病延迟强化瘢痕体积快速(每幅图像0.15秒)且与人工定量高度相关(r=0.88)。
  • 识别瘢痕负荷>15%的患者准确率达98%(202/207,95%CI:95%,99%)。
  • 三维卷积神经网络分割Dice相似系数在不同厂商间表现相当(P=.07),且高于二维卷积神经网络(0.54±0.26 vs 0.48±0.29,P=.02)。

核心结论

  • 在肥厚型心肌病人群中,三维卷积神经网络可快速、准确地定量心肌瘢痕体积,性能优于二维卷积神经网络,且在不同厂商间表现相当。

研究设计与样本

  • 回顾性研究,纳入7个中心、3个厂商的肥厚型心肌病延迟强化MRI数据,采集时间为2001年11月至2011年11月,共1073例患者(733例男性,平均年龄49岁±17)。
  • 采用基于U-Net架构的深度三维卷积神经网络进行瘢痕定量,训练集与测试集按4:1比例独立划分。
  • 短轴MRI层面堆栈拆分为重叠子堆栈,分割后合并为单一容积;以核心实验室人工瘢痕定量为参考标准,采用Dice相似系数、Pearson相关和Bland-Altman分析评估性能。

关键影像表现/征象

  • 三维卷积神经网络定量与人工瘢痕体积定量相关r=0.88(P<.001),与瘢痕体积占左心室心肌总体积比例(%LGE)相关r=0.91(P<.001)。
  • 各中心和厂商的三维卷积神经网络定量与人工定量瘢痕体积相关r=0.82-0.99(P<.001),%LGE相关r=0.90-0.97(P<.001)。
  • 二维卷积神经网络较三维卷积神经网络低估瘢痕体积(r=0.85,P<.001)和%LGE(r=0.83,P<.001)。

诊断标准与关键数值

  • 三维卷积神经网络识别大瘢痕负荷(>15%)患者的准确率为98%(202/207,95%CI:95%,99%)。
  • 三维卷积神经网络分割Dice相似系数为0.54±0.26,二维卷积神经网络为0.48±0.29(P=.02)。
  • 三维卷积神经网络Dice相似系数在不同厂商间表现相当(P=.07)。

临床应用与阅片要点

  • 三维卷积神经网络可用于肥厚型心肌病延迟强化MRI瘢痕体积的快速自动定量,每幅图像耗时0.15秒。
  • 三维卷积神经网络在不同厂商设备间分割性能相当,支持其多厂商应用。
  • 二维卷积神经网络会低估瘢痕体积和%LGE,三维卷积神经网络分割性能优于二维卷积神经网络。

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

Background Cardiac MRI late gadolinium enhancement (LGE) scar volume is an important marker for outcome prediction in patients with hypertrophic cardiomyopathy (HCM); however, its clinical application is hindered by a lack of measurement standardization. Purpose To develop and evaluate a three-dimensional (3D) convolutional neural network (CNN)-based method for automated LGE scar quantification in patients with HCM. Materials and Methods We retrospectively identified LGE MRI data in a multicenter (n = 7) and multivendor (n = 3) HCM study obtained between November 2001 and November 2011. A deep 3D CNN based on U-Net architecture was used for LGE scar quantification. Independent CNN training and testing data sets were maintained with a 4:1 ratio. Stacks of short-axis MRI slices were split into overlapping substacks that were segmented and then merged into one volume. The 3D CNN per-site and per-vendor performances were evaluated with respect to manual scar quantification performed in a core laboratory setting using Dice similarity coefficient (DSC), Pearson correlation, and Bland-Altman analyses. Furthermore, the performance of 3D CNN was compared with that of two-dimensional (2D) CNN. Results This study included 1073 patients with HCM (733 men; mean age, 49 years ± 17 [standard deviation]). The 3D CNN-based quantification was fast (0.15 second per image) and demonstrated excellent correlation with manual scar volume quantification (r = 0.88, P < .001) and ratio of scar volume to total left ventricle myocardial volume (%LGE) (r = 0.91, P < .001). The 3D CNN-based quantification strongly correlated with manual quantification of scar volume (r = 0.82-0.99, P < .001) and %LGE (r = 0.90-0.97, P < .001) for all sites and vendors. The 3D CNN identified patients with a large scar burden (>15%) with 98% accuracy (202 of 207) (95% confidence interval [CI]: 95%, 99%). When compared with 3D CNN, 2D CNN underestimated scar volume (r = 0.85, P < .001) and %LGE (r = 0.83, P < .001). The DSC of 3D CNN segmentation was comparable among different vendors (P = .07) and higher than that of 2D CNN (DSC, 0.54 ± 0.26 vs 0.48 ± 0.29; P = .02). Conclusion In the hypertrophic cardiomyopathy population, a three-dimensional convolutional neural network enables fast and accurate quantification of myocardial scar volume, outperforms a two-dimensional convolutional neural network, and demonstrates comparable performance across different vendors. © RSNA, 2019 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Fahmy AS, Neisius U, Chan RH, et al. Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study. Radiology. 2019. PMID: 31714190. doi:10.1148/radiol.2019190737

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。