Rapid prediction of MRI-induced RF heating of active implantable medical devices using machine learning.
Rapid prediction of MRI-induced RF heating of active implantable medical devices using machine learning.
复制标题
使用机器学习快速预测 MRI 引起的有源植入式医疗设备的射频加热。
DOI：
10.1109/embc40787.2023.10340900
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Golestanirad,Laleh
中科院分区：
文献类型：
--
作者：
Vu,Jasmine;Sanpitak,Pia;Bhusal,Bhumi;Jiang,Fuchang;Golestanirad,Laleh
有源植入式医疗设备与磁共振成像 (MRI) 射频 (RF) 场之间的相互作用可能会导致组织过度加热。预测存在植入物时射频加热的现有方法依赖于广泛的模型实验或电磁 (EM) 模拟，对 MR 环境、患者或植入物有不同程度的近似。相反，快速磁共振测温技术可以提供导电植入物附近组织温升的可靠实时图。在这项概念验证研究中，我们研究了基于机器学习 (ML) 的模型是否可以仅根据几秒钟的实验测量温度值来预测射频暴露几分钟后植入导线尖端附近组织的温度升高。我们使用商用深部脑刺激 (DBS) 系统进行了模型实验，以训练完全连接的前馈神经网络 (NN)，仅使用前 5 秒的数据来预测 3 T 扫描仪扫描约 3 分钟后的温度上升。对于测试数据集中的预测，神经网络有效地预测了 ΔTmax—R2= 0.99。我们的模型还显示了预测其他各种场景的射频加热的潜力，包括不同场强（1.5 T MRI，R2 = 0.87）、不同场极化（1.2 T 垂直 MRI，R2 = 0.79）和看不见的植入物（1.5 T MRI 下的心脏导联，R2 = 0.91）的 DBS 系统。我们的结果表明，将机器学习与快速 MR 测温技术相结合，在各种 MR 环境中快速预测植入物的 RF 加热具有巨大潜力。临床相关性 - 基于机器学习的算法有可能在各种 MR 环境中存在未知 AIMD 的情况下快速预测 MRI 引起的 RF 加热。
The interaction between an active implantable medical device and magnetic resonance imaging (MRI) radiofrequency (RF) fields can cause excessive tissue heating. Existing methods for predicting RF heating in the presence of an implant rely on either extensive phantom experiments or electromagnetic (EM) simulations with varying degrees of approximation of the MR environment, the patient, or the implant. On the contrary, fast MR thermometry techniques can provide a reliable real-time map of temperature rise in the tissue in the vicinity of conductive implants. In this proof-of-concept study, we examined whether a machine learning (ML) based model could predict the temperature increase in the tissue near the tip of an implanted lead after several minutes of RF exposure based on only a few seconds of experimentally measured temperature values. We performed phantom experiments with a commercial deep brain stimulation (DBS) system to train a fully connected feedforward neural network (NN) to predict temperature rise after ~3 minutes of scanning at a 3 T scanner using only data from the first 5 seconds. The NN effectively predicted ΔTmax—R2= 0.99 for predictions in the test dataset. Our model also showed potential in predicting RF heating for other various scenarios, including a DBS system at a different field strength (1.5 T MRI, R2= 0.87), different field polarization (1.2 T vertical MRI, R2= 0.79), and an unseen implant (cardiac leads at 1.5 T MRI, R2= 0.91). Our results indicate great potential for the application of ML in combination with fast MR thermometry techniques for rapid prediction of RF heating for implants in various MR environments.Clinical Relevance— Machine learning-based algorithms can potentially enable rapid prediction of MRI-induced RF heating in the presence of unknown AIMDs in various MR environments.