Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies
Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies
复制标题
DOI：
10.1097/rli.0000000000000755
复制
发表时间：
2021-06-01
影响因子：
6.7
通讯作者：
Gatidis, Sergios
中科院分区：
文献类型：
--
作者：
Kart, Turkay;Fischer, Marc;Gatidis, Sergios
本研究的目的是训练和评估深度学习模型，用于在英国生物库(UKBB)和德国国家队列(GNC)磁共振成像研究的全身磁共振(MR)图像中自动分割腹部器官，并将这些模型提供给科学界用于分析这些数据集。方法收集UKBB和GNC健康志愿者各200个T1加权图像数据集，共计400个数据集。在所有400个数据集上手动分割肝、脾、左右肾和胰腺，为训练先前描述的用于自动医学图像分割的基于U-Net的深度学习框架(NNU-Net)提供标记的地面真实数据。使用4次交叉验证方案在所有数据集上对训练好的模型进行测试。可视化地对自动分割结果进行定性分析；计算自动分割结果与手动分割结果之间的性能指标以进行定量分析。此外，在数据的一个子集上评估了两个人类读取者之间的观察者间分割可变性。结果在UKBB和GNC数据上实现了腹部器官的自动分割，具有较高的定性和定量精度。在超过90%的数据集中，没有或只有很小的视觉上可检测的定性分割错误发生。在UKBB和GNC数据上，自动分割与手动参考分割相比，肝、脾和肾脏的平均Dice分数远高于0.9，而在UKBB和GNC数据上，胰腺的平均Dice分数分别约为0.82和0.89。肝、脾和肾的平均对称表面距离在0.3-1.5 mm之间，胰腺分割在2-2.2 mm之间。自动分割的定量准确性与两个人类阅读器对所有器官的UKBB和GNC数据的一致性相当。结论利用UKBB和GNC采集的全身MR图像数据，可以实现腹部器官的自动分割，具有较高的定性和定量准确率。本研究所获得的结果和训练的深度学习模型可以作为对UKBB和GNC的数千个MR数据集进行自动分析的基础，从而有助于解决主题和原创性的科学问题。
PurposeThe 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. MethodsA 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. ResultsAutomated 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. ConclusionAutomated 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.