Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, 466-8555, Japan; Department of Computer Science, Faculty of Informatics & Computer Science, The British University in Egypt, Cairo, 11837, Egypt; Department of Mathematics, Faculty of Science, Suez Canal University, Ismailia, 41522, Egypt.
Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, 466-8555, Japan.
Neuroimage. 2019 Nov 15;202:116132. doi: 10.1016/j.neuroimage.2019.116132. Epub 2019 Aug 28.
The development of personalized human head models from medical images has become an important topic in the electromagnetic dosimetry field, including the optimization of electrostimulation, safety assessments, etc. Human head models are commonly generated via the segmentation of magnetic resonance images into different anatomical tissues. This process is time consuming and requires special experience for segmenting a relatively large number of tissues. Thus, it is challenging to accurately compute the electric field in different specific brain regions. Recently, deep learning has been applied for the segmentation of the human brain. However, most studies have focused on the segmentation of brain tissue only and little attention has been paid to other tissues, which are considerably important for electromagnetic dosimetry. In this study, we propose a new architecture for a convolutional neural network, named ForkNet, to perform the segmentation of whole human head structures, which is essential for evaluating the electrical field distribution in the brain. The proposed network can be used to generate personalized head models and applied for the evaluation of the electric field in the brain during transcranial magnetic stimulation. Our computational results indicate that the head models generated using the proposed network exhibit strong matching with those created via manual segmentation in an intra-scanner segmentation task.
从医学图像中开发个性化的人头模型已成为电磁剂量学领域的一个重要课题，包括电刺激优化、安全性评估等。人头模型通常通过将磁共振图像分割成不同的解剖组织来生成。这个过程耗时且需要特殊经验来分割相对大量的组织。因此，准确计算不同特定脑区的电场具有挑战性。最近，深度学习已应用于人脑的分割。然而，大多数研究都集中在脑组织的分割上，而很少关注对电磁剂量学非常重要的其他组织。在这项研究中，我们提出了一种名为 ForkNet 的卷积神经网络的新架构，用于分割整个人头结构，这对于评估大脑中的电场分布至关重要。该网络可用于生成个性化的头模型，并应用于经颅磁刺激期间大脑电场的评估。我们的计算结果表明，使用所提出的网络生成的头模型在内部扫描仪分割任务中与通过手动分割创建的模型具有很强的匹配性。
