Machine learning based white matter models with permeability: An experimental study in cuprizone treated in-vivo mouse model of axonal demyelination
Machine learning based white matter models with permeability: An experimental study in cuprizone treated in-vivo mouse model of axonal demyelination
复制标题
DOI：
10.1016/j.neuroimage.2020.117425
复制
发表时间：
2021-01-01
期刊：
影响因子：
5.7
通讯作者：
Drobnjak, Ivana
中科院分区：
文献类型：
--
作者：
Hill, Ioana;Palombo, Marco;Drobnjak, Ivana
轴突内水交换时间（tau（i））是与轴突渗透性相关的参数，可以是用于理解和治疗脱髓鞘病理如多发性硬化症的重要生物标志物。扩散加权MRI（DW-MRI）对渗透性的变化很敏感;然而，由于缺乏包含它的一般生物物理模型，该参数迄今为止仍然难以捉摸。基于机器学习的计算模型可以潜在地用于估计这些参数。最近，第一次，一个理论框架，使用随机森林（RF）回归表明，这是一个有前途的渗透率估计的新方法。在这项研究中，我们采用这样的方法，并首次通过与histology.We直接比较实验研究它的脱髓鞘病理构造一个计算模型，使用蒙特卡罗模拟和RF回归，以学习来自DW-MRI信号和地面真实微观结构参数的功能之间的映射。我们在模拟中测试了我们的模型，并发现预测参数和真实参数之间存在很强的相关性（轴突内体积分数f：R-2 = 0.99，tau（i）：R-2 = 0.84，固有扩散率d：R-2 = 0.99）。然后，我们将该模型应用于脱髓鞘的对照cuprizone（CPZ）小鼠模型的体内，比较来自两组小鼠CPZ（N=8）和健康年龄匹配的野生型（WT，N=8）的结果。我们发现，RF模型估计敏感的微观结构参数为这两组，在文献中发现的匹配值。此外，我们使用电子显微镜（EM）对两组进行组织学检查，测量髓鞘厚度作为交换时间的替代。组织学结果表明，我们的RF模型估计值与EM测量值非常强相关（f的rho = 0.98，tau（i）的rho = 0.82）。最后，我们发现与WT组（= 370 ms/370 ms/380 ms）相比，CPZ组（= 310 ms/330 ms/350 ms）的胼胝体（压部/腹侧/体部）的所有三个区域中的tau（i）在统计学上显著降低。这与我们的预期一致，即tau（i）在髓鞘受损的区域较低，因为轴突膜变得更具渗透性。总之，这些结果首次在实验和体内证明，从模拟中学习的计算模型可以可靠地估计微结构参数，包括轴突渗透性。
The intra-axonal water exchange time (tau(i)), a parameter associated with axonal permeability, could be an important biomarker for understanding and treating demyelinating pathologies such as Multiple Sclerosis. Diffusion-Weighted MRI (DW-MRI) is sensitive to changes in permeability; however, the parameter has so far remained elusive due to the lack of general biophysical models that incorporate it. Machine learning based computational models can potentially be used to estimate such parameters. Recently, for the first time, a theoretical framework using a random forest (RF) regressor suggests that this is a promising new approach for permeability estimation. In this study, we adopt such an approach and for the first time experimentally investigate it for demyelinating pathologies through direct comparison with histology.We construct a computational model using Monte Carlo simulations and an RF regressor in order to learn a mapping between features derived from DW-MRI signals and ground truth microstructure parameters. We test our model in simulations, and find strong correlations between the predicted and ground truth parameters (intra-axonal volume fraction f: R-2 = 0.99, tau(i): R-2 = 0.84, intrinsic diffusivity d: R-2 = 0.99). We then apply the model in-vivo, on a controlled cuprizone (CPZ) mouse model of demyelination, comparing the results from two cohorts of mice, CPZ (N=8) and healthy age-matched wild-type (WT, N=8). We find that the RF model estimates sensible microstructure parameters for both groups, matching values found in literature. Furthermore, we perform histology for both groups using electron microscopy (EM), measuring the thickness of the myelin sheath as a surrogate for exchange time. Histology results show that our RF model estimates are very strongly correlated with the EM measurements (rho = 0.98 for f, rho = 0.82 for tau(i)). Finally, we find a statistically significant decrease in tau(i) in all three regions of the corpus callosum (splenium/genu/body) of the CPZ cohort ( = 310ms/330ms/350ms) compared to the WT group ( = 370ms/370ms/380ms). This is in line with our expectations that tau(i) is lower in regions where the myelin sheath is damaged, as axonal membranes become more permeable. Overall, these results demonstrate, for the first time experimentally and in vivo, that a computational model learned from simulations can reliably estimate microstructure parameters, including the axonal permeability