Abstract：
BACKGROUND: Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge.
METHODS: Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise \"uncertainty map\" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the \"best\" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).
RESULTS: The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with \"failed\" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005).
CONCLUSIONS: The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.
METHODS: Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise \"uncertainty map\" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the \"best\" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).
RESULTS: The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with \"failed\" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005).
CONCLUSIONS: The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.
摘要：
背景：心肌灌注MRI数据集的全自动分析可以快速客观地报告疑似缺血性心脏病患者的压力/休息研究。尽管训练数据有限，软件（脉冲序列）和硬件（扫描仪供应商）的变化，开发可以分析多中心数据集的深度学习技术是一个持续的挑战。
方法：包括在3T（n=150名受试者；21,150张首传图像）从3个医疗中心获取的数据集：内部数据集（inD；n=95）和两个外部数据集（exD；n=55），用于评估训练的深度神经网络（DNN）模型对脉冲序列（exD-1）和扫描仪供应商（exD-2）差异的鲁棒性。IND的子集（n=85）用于训练/验证用于分割的DNN池，所有使用相同的时空U-Net架构和超参数，但具有不同的参数初始化。我们采用了时空滑动补丁分析方法，该方法自动生成像素级的“不确定性图”作为分割过程的副产品。在我们的方法中，被称为数据自适应不确定性引导时空(DAUGS)分析，给定的测试用例由DNN池的所有成员分段，并利用产生的不确定性图来自动选择解决方案池中的“最佳”之一。为了比较，我们还使用具有相同设置的既定方法训练了DNN(超参数，数据增强，等。).
结果：建议的DAUGS分析方法与内部数据集上已建立的方法相似（inD测试子集的Dice评分：0.896±0.050vs.0.890±0.049；p=n.s.），而它在外部数据集上的表现明显优于（exD-1的骰子：0.885±0.040与0.849±0.065，p<0.005；exD-2的骰子：0.811±0.070vs.0.728±0.149，p<0.005)。此外，与“失败”分割的图像系列的数量（定义为具有包括血池或在≥1段中不连续的心肌轮廓）明显较低。既定方法(4.3%与17.1%,p<0.0005)。
结论：所提出的DAUGS分析方法有可能提高深度学习方法的鲁棒性，以分割具有脉冲序列选择变化的多中心应力灌注数据集，站点位置或扫描仪供应商。
方法：包括在3T（n=150名受试者；21,150张首传图像）从3个医疗中心获取的数据集：内部数据集（inD；n=95）和两个外部数据集（exD；n=55），用于评估训练的深度神经网络（DNN）模型对脉冲序列（exD-1）和扫描仪供应商（exD-2）差异的鲁棒性。IND的子集（n=85）用于训练/验证用于分割的DNN池，所有使用相同的时空U-Net架构和超参数，但具有不同的参数初始化。我们采用了时空滑动补丁分析方法，该方法自动生成像素级的“不确定性图”作为分割过程的副产品。在我们的方法中，被称为数据自适应不确定性引导时空(DAUGS)分析，给定的测试用例由DNN池的所有成员分段，并利用产生的不确定性图来自动选择解决方案池中的“最佳”之一。为了比较，我们还使用具有相同设置的既定方法训练了DNN(超参数，数据增强，等。).
结果：建议的DAUGS分析方法与内部数据集上已建立的方法相似（inD测试子集的Dice评分：0.896±0.050vs.0.890±0.049；p=n.s.），而它在外部数据集上的表现明显优于（exD-1的骰子：0.885±0.040与0.849±0.065，p<0.005；exD-2的骰子：0.811±0.070vs.0.728±0.149，p<0.005)。此外，与“失败”分割的图像系列的数量（定义为具有包括血池或在≥1段中不连续的心肌轮廓）明显较低。既定方法(4.3%与17.1%,p<0.0005)。
结论：所提出的DAUGS分析方法有可能提高深度学习方法的鲁棒性，以分割具有脉冲序列选择变化的多中心应力灌注数据集，站点位置或扫描仪供应商。
