Machine learning-based prediction of MRI-induced power absorption in the tissue in patients with simplified deep brain stimulation lead models.
Machine learning-based prediction of MRI-induced power absorption in the tissue in patients with simplified deep brain stimulation lead models.
复制标题
DOI：
10.1109/temc.2021.3106872
复制
发表时间：
2021-10
影响因子：
2.1
通讯作者：
Golestanirad L
中科院分区：
文献类型：
--
作者：
Vu J;Nguyen BT;Bhusal B;Baraboo J;Rosenow J;Bagci U;Bright MG;Golestanirad L
有源电子植入物（如脑深部电刺激（DBS）系统）与MRI射频场的相互作用可能导致组织过热，从而限制MRI可及性。量化射频加热的努力主要依赖于电磁（EM）模拟来评估个体化的比吸收率（SAR），但此类模拟需要大量的计算资源。在这里，我们研究了使用机器学习（ML）的预测模型是否可以根据MRI入射电场Etan的切向分量分布预测植入电极导线尖端周围组织中的局部SAR。构建了260个独特的患者源性和人工DBS电极导线轨迹的数据集，并通过EM模拟确定了1.5 T MRI期间电极导线尖端的1g平均SAR（1gSARmax）。沿每个电极导线轨迹的Etan值沿着和模拟SAR值用于训练和测试ML算法。ML算法的预测结果表明，Etan分布可有效预测DBS电极导线头端的1gSARmax（R = 0.82）。我们的研究结果表明，ML有可能提供一种快速的方法来预测MR诱导的功率吸收周围的组织中的尖端植入的导线，如那些在有源电子医疗设备。
Interaction of an active electronic implant such as a deep brain stimulation (DBS) system and MRI RF fields can induce excessive tissue heating, limiting MRI accessibility. Efforts to quantify RF heating mostly rely on electromagnetic (EM) simulations to assess individualized specific absorption rate (SAR), but such simulations require extensive computational resources. Here, we investigate if a predictive model using machine learning (ML) can predict the local SAR in the tissue around tips of implanted leads from the distribution of the tangential component of the MRI incident electric field, Etan. A dataset of 260 unique patient-derived and artificial DBS lead trajectories was constructed, and the 1 g-averaged SAR, 1gSARmax, at the lead-tip during 1.5 T MRI was determined by EM simulations. Etan values along each lead’s trajectory and the simulated SAR values were used to train and test the ML algorithm. The resulting predictions of the ML algorithm indicated that the distribution of Etan could effectively predict 1gSARmax at the DBS lead-tip (R = 0.82). Our results indicate that ML has the potential to provide a fast method for predicting MR-induced power absorption in the tissue around tips of implanted leads such as those in active electronic medical devices.
登录
查看更多内容
影响因子：
3.3
作者：
Golestanirad, Laleh;Kazemivalipour, Ehsan;Kirsch, John
通讯作者：
Kirsch, John
影响因子：
5.7
作者：
Kazemivalipour, Ehsan;Keil, Boris;Golestanirad, Laleh
通讯作者：
Golestanirad, Laleh
影响因子：
3.3
作者：
McElcheran, Clare E.;Yang, Benson;Graham, Simon J.
通讯作者：
Graham, Simon J.
影响因子：
3.7
作者：
Iacono MI;Neufeld E;Akinnagbe E;Bower K;Wolf J;Vogiatzis Oikonomidis I;Sharma D;Lloyd B;Wilm BJ;Wyss M;Pruessmann KP;Jakab A;Makris N;Cohen ED;Kuster N;Kainz W;Angelone LM
通讯作者：
Angelone LM
影响因子：
4.6
作者：
Lucano, Elena;Liberti, Micaela;Angelone, Leonardo M.
通讯作者：
Angelone, Leonardo M.