Ulas Cagdas, Das Dhritiman, Thrippleton Michael J, Valdés Hernández Maria Del C, Armitage Paul A, Makin Stephen D, Wardlaw Joanna M, Menze Bjoern H
Department of Computer Science, Technische Universität München, Munich, Germany.
GE Global Research, Munich, Germany.
Front Neurol. 2019 Jan 8;9:1147. doi: 10.3389/fneur.2018.01147. eCollection 2018.
The T1-weighted dynamic contrast enhanced (DCE)-MRI is an imaging technique that provides a quantitative measure of pharmacokinetic (PK) parameters characterizing microvasculature of tissues. For the present study, we propose a new machine learning (ML) based approach to directly estimate the PK parameters from the acquired DCE-MRI image-time series that is both more robust and faster than conventional model fitting. We specifically utilize deep convolutional neural networks (CNNs) to learn the mapping between the image-time series and corresponding PK parameters. DCE-MRI datasets acquired from 15 patients with clinically evident mild ischaemic stroke were used in the experiments. Training and testing were carried out based on leave-one-patient-out cross- validation. The parameter estimates obtained by the proposed CNN model were compared against the two tracer kinetic models: (1) Patlak model, (2) Extended Tofts model, where the estimation of model parameters is done via voxelwise linear and nonlinear least squares fitting respectively. The trained CNN model is able to yield PK parameters which can better discriminate different brain tissues, including stroke regions. The results also demonstrate that the model generalizes well to new cases even if a subject specific arterial input function (AIF) is not available for the new data. A ML-based model can be used for direct inference of the PK parameters from DCE image series. This method may allow fast and robust parameter inference in population DCE studies. Parameter inference on a 3D volume-time series takes only a few seconds on a GPU machine, which is significantly faster compared to conventional non-linear least squares fitting.
T1加权动态对比增强（DCE）-MRI是一种成像技术，可对表征组织微血管系统的药代动力学（PK）参数进行定量测量。在本研究中，我们提出了一种基于机器学习（ML）的新方法，可直接从采集的DCE-MRI图像时间序列中估计PK参数，该方法比传统模型拟合更稳健、更快。我们特别利用深度卷积神经网络（CNN）来学习图像时间序列与相应PK参数之间的映射关系。实验中使用了从15例临床诊断为轻度缺血性中风患者获取的DCE-MRI数据集。基于留一患者交叉验证进行训练和测试。将所提出的CNN模型获得的参数估计值与两种示踪剂动力学模型进行比较：（1）Patlak模型，（2）扩展Tofts模型，其中模型参数的估计分别通过体素线性和非线性最小二乘拟合完成。训练后的CNN模型能够产生PK参数，这些参数能够更好地区分不同的脑组织，包括中风区域。结果还表明，即使新数据没有特定受试者的动脉输入函数（AIF），该模型对新病例也具有良好的泛化能力。基于ML的模型可用于从DCE图像序列中直接推断PK参数。该方法可能允许在群体DCE研究中进行快速且稳健的参数推断。在GPU机器上，对三维体积时间序列进行参数推断仅需几秒钟，这比传统的非线性最小二乘拟合要快得多。
