文献速递心血管MR

使用市售深度学习算法在心脏磁共振成像中自动测量原生T1和细胞外容积分数

Automated Measurement of Native T1 and Extracellular Volume Fraction in Cardiac Magnetic Resonance Imaging Using a Commercially Available Deep Learning Algorithm.
PubMed 文献 · Korean J Radiol · 2022-01-01

本研究纳入95名参与者(左心室肥厚36例、扩张型心肌病32例、健康志愿者27例)的心脏磁共振图像,测试基于2D U-net的市售深度学习算法自动测量原生T1和细胞外容积分数(ECV),并与两名专家读者手动分析的共识参考标准比较;深度学习在原生T1图99.3%的切片和增强后T1图89.8%的切片上成功分割心肌,自动测量与参考标准的相关性和一致性良好,与四位放射科医生的测量结果相当。

要点

  • 深度学习算法在原生T1图99.3%的切片和增强后T1图89.8%的切片上成功分割心肌。
  • 自动测量与参考标准在原生T1(r=0.967)和ECV(r=0.987)上均呈强相关。
  • 自动测量与四位放射科医生的一致性(ICC 0.98-0.99)与放射科医生之间的一致性相当。

核心结论

  • 该深度学习算法可实现与放射科医生相当的自动T1和ECV测量。

研究设计与样本

  • 研究纳入95名参与者的心脏磁共振图像,包括左心室肥厚36例(肥厚型心肌病12例、法布雷病12例、淀粉样变性12例)、扩张型心肌病32例和健康志愿者27例;使用基于2D U-net的市售深度学习算法(Myomics-T1软件,版本1.0.0)自动分析T1图,由四名放射科医生作为研究读者进行手动分析,参考标准为另外两名专家读者手动分析的共识结果。

关键影像表现/征象

  • 深度学习在原生T1图中成功分割99.3%的切片,在增强后T1图中成功分割89.8%的切片。
  • 原生T1图的Dice相似系数为0.86 ± 0.05,增强后T1图为0.74 ± 0.17。
  • 按受试者分析,自动测量与参考标准在原生T1的相关系数r=0.967(95%CI 0.951-0.978),偏倚9.5毫秒(95%一致性界限 -23.6至42.6毫秒)。
  • 按受试者分析,自动测量与参考标准在ECV的相关系数r=0.987(95%CI 0.980-0.991),偏倚0.7%(95%一致性界限 -2.8%至4.2%)。

诊断标准与关键数值

  • 原生T1自动测量与参考标准的相关系数r=0.967(95%CI 0.951-0.978),偏倚9.5毫秒(95%一致性界限 -23.6至42.6毫秒)。
  • ECV自动测量与参考标准的相关系数r=0.987(95%CI 0.980-0.991),偏倚0.7%(95%一致性界限 -2.8%至4.2%)。
  • 深度学习与四位放射科医生之间原生T1和ECV的组内相关系数(ICC)均为0.98-0.99。
  • 四位放射科医生两两之间原生T1的ICC为0.97-1.00,ECV的ICC为0.99-1.00。

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: T1 mapping provides valuable information regarding cardiomyopathies. Manual drawing is time consuming and prone to subjective errors. Therefore, this study aimed to test a DL algorithm for the automated measurement of native T1 and extracellular volume (ECV) fractions in cardiac magnetic resonance (CMR) imaging with a temporally separated dataset.

MATERIALS AND METHODS: CMR images obtained for 95 participants (mean age ± standard deviation, 54.5 ± 15.2 years), including 36 left ventricular hypertrophy (12 hypertrophic cardiomyopathy, 12 Fabry disease, and 12 amyloidosis), 32 dilated cardiomyopathy, and 27 healthy volunteers, were included. A commercial deep learning (DL) algorithm based on 2D U-net (Myomics-T1 software, version 1.0.0) was used for the automated analysis of T1 maps. Four radiologists, as study readers, performed manual analysis. The reference standard was the consensus result of the manual analysis by two additional expert readers. The segmentation performance of the DL algorithm and the correlation and agreement between the automated measurement and the reference standard were assessed. Interobserver agreement among the four radiologists was analyzed.

RESULTS: DL successfully segmented the myocardium in 99.3% of slices in the native T1 map and 89.8% of slices in the post-T1 map with Dice similarity coefficients of 0.86 ± 0.05 and 0.74 ± 0.17, respectively. Native T1 and ECV showed strong correlation and agreement between DL and the reference: for T1, r = 0.967 (95% confidence interval [CI], 0.951-0.978) and bias of 9.5 msec (95% limits of agreement [LOA], -23.6-42.6 msec); for ECV, r = 0.987 (95% CI, 0.980-0.991) and bias of 0.7% (95% LOA, -2.8%-4.2%) on per-subject basis. Agreements between DL and each of the four radiologists were excellent (intraclass correlation coefficient [ICC] of 0.98-0.99 for both native T1 and ECV), comparable to the pairwise agreement between the radiologists (ICC of 0.97-1.00 and 0.99-1.00 for native T1 and ECV, respectively).

CONCLUSION: The DL algorithm allowed automated T1 and ECV measurements comparable to those of radiologists.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Chang S, Han K, Lee S, et al. Automated Measurement of Native T1 and Extracellular Volume Fraction in Cardiac Magnetic Resonance Imaging Using a Commercially Available Deep Learning Algorithm. Korean J Radiol. 2022. PMID: 36447413. doi:10.3348/kjr.2022.0496

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。