Erturk M Arcan, Panken Eric, Conroy Mark J, Edmonson Jonathan, Kramer Jeff, Chatterton Jacob, Banerjee S Riki
Restorative Therapies Group, Implantables R&D, Medtronic PLC, Minneapolis, MN, United States.
Cardiac Rhythm Heart Failure, Device Product Engineering, Medtronic PLC, Minneapolis, MN, United States.
Front Hum Neurosci. 2020 Feb 20;14:34. doi: 10.3389/fnhum.2020.00034. eCollection 2020.
MRI gradient-fields may induce extrinsic voltage between electrodes and conductive neurostimulator enclosure of implanted deep brain stimulation (DBS) systems, and may cause unintended stimulation and/or malfunction. Electromagnetic (EM) simulations using detailed anatomical human models, therapy implant trajectories, and gradient coil models can be used to calculate clinically relevant induced voltage levels. Incorporating additional anatomical human models into the EM simulation library can help to achieve more clinically relevant and accurate induced voltage levels, however, adding new anatomical human models and developing implant trajectories is time-consuming, expensive and not always feasible.
MRI gradient-field induced voltage levels are simulated in six adult human anatomical models, along clinically relevant DBS implant trajectories to generate the dataset. Predictive artificial neural network (ANN) regression models are trained on the simulated dataset. Leave-one-out cross validation is performed to assess the performance of ANN regressors and quantify model prediction errors.
More than 180,000 unique gradient-induced voltage levels are simulated. ANN algorithm with two fully connected layers is selected due to its superior generalizability compared to support vector machine and tree-based algorithms in this particular application. The ANN regression model is capable of producing thousands of gradient-induced voltage predictions in less than a second with mean-squared-error less than 200 mV.
We have integrated machine learning (ML) with computational modeling and simulations and developed an accurate predictive model to determine MRI gradient-field induced voltage levels on implanted DBS systems.
磁共振成像（MRI）梯度场可能会在植入式深部脑刺激（DBS）系统的电极与导电神经刺激器外壳之间感应出外部电压，并可能导致意外刺激和/或故障。使用详细的人体解剖模型、治疗植入轨迹和梯度线圈模型进行电磁（EM）模拟，可用于计算临床相关的感应电压水平。将额外的人体解剖模型纳入EM模拟库有助于获得更具临床相关性和准确性的感应电压水平，然而，添加新的人体解剖模型和开发植入轨迹既耗时又昂贵，而且并不总是可行的。
在六个成人人体解剖模型中，沿着临床相关的DBS植入轨迹模拟MRI梯度场感应电压水平，以生成数据集。在模拟数据集上训练预测人工神经网络（ANN）回归模型。进行留一法交叉验证，以评估ANN回归器的性能并量化模型预测误差。
模拟了超过180,000个独特的梯度感应电压水平。由于在该特定应用中，与支持向量机和基于树的算法相比，具有两个全连接层的ANN算法具有更高的通用性，因此被选中。ANN回归模型能够在不到一秒的时间内产生数千个梯度感应电压预测，均方误差小于200 mV。
我们将机器学习（ML）与计算建模和模拟相结合，开发了一种准确预测模型，以确定植入式DBS系统上MRI梯度场感应电压水平。
