文献速递腹部泌尿生殖MR

基于深度学习的UK Biobank与德国国家队列MRI腹部器官自动分割

Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies.
PubMed 文献 · Invest Radiol · 2021-01-01

本研究利用UKBB和GNC各200例健康志愿者T1加权MR图像,训练U-Net框架nnU-Net自动分割肝、脾、双肾和胰腺,采用4折交叉验证。自动分割在超过90%的数据集中无或仅轻微定性错误,肝脾肾Dice均>0.9,胰腺约0.82和0.89,定量精度与两位读者间一致性相当。

要点

  • 自动分割在>90%数据集中无或仅轻微定性错误。
  • 肝脾肾Dice>0.9,胰腺Dice约0.82(UKBB)和0.89(GNC)。
  • 定量精度与两位人类读者间一致性相当。

核心结论

  • 自动分割在UKBB和GNC全身MR图像上具有高定性和定量精度,模型可作为大规模自动分析的基础。

研究设计与样本

  • 研究类型为深度学习模型训练与评估,样本共400例T1加权MR数据集(UKBB和GNC各200例健康志愿者)。
  • 手动分割肝、脾、左肾、右肾和胰腺作为标注 ground truth,训练nnU-Net框架。
  • 采用4折交叉验证在所有数据集上测试,并评估2位人类读者间分割变异性。

关键影像表现/征象

  • 在超过90%的数据集中,自动分割无或仅轻微视觉可检测的定性错误。

诊断标准与关键数值

  • 肝、脾、肾自动分割与手动参考的平均Dice评分在UKBB和GNC数据上均远高于0.9。
  • 胰腺平均Dice评分在UKBB约0.82、在GNC约0.89。
  • 肝、脾、肾的平均对称表面距离为0.3–1.5 mm,胰腺为2–2.2 mm。
  • 自动分割的定量精度与2位人类读者间一致性相当(所有器官)。

临床应用与阅片要点

  • 日常阅片可借助自动分割快速获得腹部器官轮廓,但需注意胰腺分割精度相对较低。

局限性

  • 仅纳入健康志愿者T1加权MR图像,未涉及病变或异常器官。
  • 4折交叉验证可能不足以全面评估泛化性。

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

PURPOSE: The aims of this study were to train and evaluate deep learning models for automated segmentation of abdominal organs in whole-body magnetic resonance (MR) images from the UK Biobank (UKBB) and German National Cohort (GNC) MR imaging studies and to make these models available to the scientific community for analysis of these data sets.

METHODS: A total of 200 T1-weighted MR image data sets of healthy volunteers each from UKBB and GNC (400 data sets in total) were available in this study. Liver, spleen, left and right kidney, and pancreas were segmented manually on all 400 data sets, providing labeled ground truth data for training of a previously described U-Net-based deep learning framework for automated medical image segmentation (nnU-Net). The trained models were tested on all data sets using a 4-fold cross-validation scheme. Qualitative analysis of automated segmentation results was performed visually; performance metrics between automated and manual segmentation results were computed for quantitative analysis. In addition, interobserver segmentation variability between 2 human readers was assessed on a subset of the data.

RESULTS: Automated abdominal organ segmentation was performed with high qualitative and quantitative accuracy on UKBB and GNC data. In more than 90% of data sets, no or only minor visually detectable qualitative segmentation errors occurred. Mean Dice scores of automated segmentations compared with manual reference segmentations were well higher than 0.9 for the liver, spleen, and kidneys on UKBB and GNC data and around 0.82 and 0.89 for the pancreas on UKBB and GNC data, respectively. Mean average symmetric surface distance was between 0.3 and 1.5 mm for the liver, spleen, and kidneys and between 2 and 2.2 mm for pancreas segmentation. The quantitative accuracy of automated segmentation was comparable with the agreement between 2 human readers for all organs on UKBB and GNC data.

CONCLUSION: Automated segmentation of abdominal organs is possible with high qualitative and quantitative accuracy on whole-body MR imaging data acquired as part of UKBB and GNC. The results obtained and deep learning models trained in this study can be used as a foundation for automated analysis of thousands of MR data sets of UKBB and GNC and thus contribute to tackling topical and original scientific questions.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Kart T, Fischer M, Küstner T, et al. Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies. Invest Radiol. 2021. PMID: 33930003. doi:10.1097/RLI.0000000000000755

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。