文献速递腹部技术与安全MR

全肝自动分割与PDFF及R2*定量在MRI上的应用

Precise whole liver automatic segmentation and quantification of PDFF and R2* on MR images.
PubMed 文献 · Eur Radiol · 2021-03-25

本研究回顾性多中心收集183例多回波化学位移编码肝脏MRI检查,训练编码器-解码器CNN进行全肝实质分割,并在内部验证集(46例)和外部验证集(29例)上评估PDFF与R2*定量性能。结果显示内部测试Dice系数0.93±0.03,外部验证(不同厂商同场强)Dice系数0.94±0.02,1.5-T同厂商扫描仪Dice系数0.87±0.06,自动与手动分割的定量相关性高(rPDFF=1,rR2*=1,p<0.001),PDFF和R2*的相对误差分别低于4%和1%。

要点

  • CNN可自动分割全肝实质,内部测试Dice系数0.93±0.03,外部验证(不同厂商)Dice系数0.94±0.02。
  • 自动分割与手动分割的PDFF和R2*定量高度相关(rPDFF=1,rR2*=1,p<0.001)。
  • PDFF和R2*的相对误差在内部和外部验证中分别低于4%和1%。

关键影像表现/征象

  • 自动分割在内部测试集Dice系数为0.93±0.03,外部验证(不同厂商同场强)Dice系数为0.94±0.02。
  • 1.5-T同厂商扫描仪外部验证Dice系数为0.87±0.06。

诊断标准与关键数值

  • 内部测试集自动与手动分割定量相关性:rPDFF=1,rR2*=1(p<0.001)。
  • 外部验证集(不同厂商同场强及1.5-T同厂商)自动与手动分割定量相关性:rPDFF=1,rR2*=1(p<0.001)。
  • 内部和外部验证集中,PDFF相对误差低于4%,R2*相对误差低于1%。

临床应用与阅片要点

  • CNN可自动分割全肝实质,生成PDFF和R2*的自动定量图,与手动分割定量高度一致。
  • 模型在不同厂商同场强扫描仪上表现良好(Dice系数0.94±0.02),提示可推广至其他制造商。
  • 在1.5-T同厂商扫描仪上Dice系数为0.87±0.06,略低于其他外部验证。

局限性

  • 原文未述局限性

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: To automate the segmentation of whole liver parenchyma on multi-echo chemical shift encoded (MECSE) MR examinations using convolutional neural networks (CNNs) to seamlessly quantify precise organ-related imaging biomarkers such as the fat fraction and iron load.

METHODS: A retrospective multicenter collection of 183 MECSE liver MR examinations was conducted. An encoder-decoder CNN was trained (107 studies) following a 5-fold cross-validation strategy to improve the model performance and ensure lack of overfitting. Proton density fat fraction (PDFF) and R2* were quantified on both manual and CNN segmentation masks. Different metrics were used to evaluate the CNN performance over both unseen internal (46 studies) and external (29 studies) validation datasets to analyze reproducibility.

RESULTS: The internal test showed excellent results for the automatic segmentation with a dice coefficient (DC) of 0.93 ± 0.03 and high correlation between the quantification done with the predicted mask and the manual segmentation (rPDFF = 1 and rR2* = 1; p values < 0.001). The external validation was also excellent with a different vendor but the same magnetic field strength, proving the generalization of the model to other manufacturers with DC of 0.94 ± 0.02. Results were lower for the 1.5-T MR same vendor scanner with DC of 0.87 ± 0.06. Both external validations showed high correlation in the quantification (rPDFF = 1 and rR2* = 1; p values < 0.001). In both internal and external validation datasets, the relative error for the PDFF and R2* quantification was below 4% and 1% respectively.

CONCLUSION: Liver parenchyma can be accurately segmented with CNN in a vendor-neutral virtual approach, allowing to obtain reproducible automatic whole organ virtual biopsies.

KEY POINTS: • Whole liver parenchyma can be automatically segmented using convolutional neural networks. • Deep learning allows the creation of automatic pipelines for the precise quantification of liver-related imaging biomarkers such as PDFF and R2*. • MR "virtual biopsy" can become a fast and automatic procedure for the assessment of chronic diffuse liver diseases in clinical practice.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Jimenez-Pastor A, Alberich-Bayarri A, Lopez-Gonzalez R, et al. Precise whole liver automatic segmentation and quantification of PDFF and R2* on MR images. Eur Radiol. 2021. PMID: 33768292. doi:10.1007/s00330-021-07838-5

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。