{"title":"基于神经网络的全头脑磁仪传感器阵列几何结构快速采集","authors":"Yoshiaki Adachi;Daisuke Oyama;Gen Uehara","doi":"10.1109/LMAG.2025.3560886","DOIUrl":null,"url":null,"abstract":"Acquiring position, orientation, and sensitivity of magnetometers in a helmet-shaped sensor array is crucial for accurate current source reconstruction in magnetoencephalography. To determine these parameters for each magnetometer, we utilize a spherical calibration coil array. In our previous study, the position and orientation of each magnetometer were determined as the solution of an inverse problem through a numerical search that minimized the difference between the theoretical magnetic field signals from each coil and the measured signals detected by the magnetometer. In this study, we applied a deep neural network to estimate the position and orientation of each magnetometer in the helmet-shaped sensor array without solving the inverse problem. A total of 223 million pairs of a given magnetometer's five parameters (<italic>x</i>, <italic>y</i>, <italic>z</i>, <italic>θ</i>, and <italic>ϕ</i>) and the corresponding theoretical magnetic field signals from the coils were used to train the neural network. The training process required approximately 53 h using a commercially available GPU-equipped computer. The trained neural network was then applied to acquire the sensor geometry from magnetic field data obtained during a conventional calibration procedure for a 160-channel whole-head magnetoencephalograph system using a spherical calibration coil array. The position and orientation of each magnetometer estimated by this method deviated by an average of 0.65 mm and 0.51°, respectively, from those obtained via the conventional inverse problem approach. The acquisition of the geometry for all 160 magnetometers required less than 8 ms. With such high-speed acquisition, this approach opens possibilities for future applications in acquiring positional information of wearable sensor arrays whose structures change in real time.","PeriodicalId":13040,"journal":{"name":"IEEE Magnetics Letters","volume":"16 ","pages":"1-5"},"PeriodicalIF":1.1000,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10964712","citationCount":"0","resultStr":"{\"title\":\"Fast Acquisition of Sensor Array Geometry of Whole-Head Magnetoencephalograph Systems Using a Neural Network\",\"authors\":\"Yoshiaki Adachi;Daisuke Oyama;Gen Uehara\",\"doi\":\"10.1109/LMAG.2025.3560886\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Acquiring position, orientation, and sensitivity of magnetometers in a helmet-shaped sensor array is crucial for accurate current source reconstruction in magnetoencephalography. To determine these parameters for each magnetometer, we utilize a spherical calibration coil array. In our previous study, the position and orientation of each magnetometer were determined as the solution of an inverse problem through a numerical search that minimized the difference between the theoretical magnetic field signals from each coil and the measured signals detected by the magnetometer. In this study, we applied a deep neural network to estimate the position and orientation of each magnetometer in the helmet-shaped sensor array without solving the inverse problem. A total of 223 million pairs of a given magnetometer's five parameters (<italic>x</i>, <italic>y</i>, <italic>z</i>, <italic>θ</i>, and <italic>ϕ</i>) and the corresponding theoretical magnetic field signals from the coils were used to train the neural network. The training process required approximately 53 h using a commercially available GPU-equipped computer. The trained neural network was then applied to acquire the sensor geometry from magnetic field data obtained during a conventional calibration procedure for a 160-channel whole-head magnetoencephalograph system using a spherical calibration coil array. The position and orientation of each magnetometer estimated by this method deviated by an average of 0.65 mm and 0.51°, respectively, from those obtained via the conventional inverse problem approach. The acquisition of the geometry for all 160 magnetometers required less than 8 ms. With such high-speed acquisition, this approach opens possibilities for future applications in acquiring positional information of wearable sensor arrays whose structures change in real time.\",\"PeriodicalId\":13040,\"journal\":{\"name\":\"IEEE Magnetics Letters\",\"volume\":\"16 \",\"pages\":\"1-5\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2025-04-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10964712\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Magnetics Letters\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10964712/\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Magnetics Letters","FirstCategoryId":"101","ListUrlMain":"https://ieeexplore.ieee.org/document/10964712/","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
摘要
获取头盔形传感器阵列中磁强计的位置、方向和灵敏度对于脑磁图中电流源的精确重建至关重要。为了确定每个磁强计的这些参数,我们使用球形校准线圈阵列。在我们之前的研究中,每个磁力计的位置和方向都是通过数值搜索来确定的,通过数值搜索来最小化每个线圈的理论磁场信号与磁力计检测到的测量信号之间的差异。在这项研究中,我们应用深度神经网络来估计头盔形传感器阵列中每个磁强计的位置和方向,而不解决逆问题。给定磁力计的五个参数(x, y, z, θ和ϕ)和线圈中相应的理论磁场信号共2.23亿对用于训练神经网络。训练过程需要大约53小时使用市售的gpu配备的计算机。然后应用训练好的神经网络从常规校准过程中获得的磁场数据中获取传感器几何形状,该过程使用球形校准线圈阵列对160通道全头脑磁仪系统进行校准。用该方法估计的每个磁强计的位置和方向与传统的反问题方法分别平均偏差0.65 mm和0.51°。所有160个磁力计的几何形状的采集需要不到8毫秒。通过这种高速采集,该方法为获取结构实时变化的可穿戴传感器阵列的位置信息开辟了未来应用的可能性。
Fast Acquisition of Sensor Array Geometry of Whole-Head Magnetoencephalograph Systems Using a Neural Network
Acquiring position, orientation, and sensitivity of magnetometers in a helmet-shaped sensor array is crucial for accurate current source reconstruction in magnetoencephalography. To determine these parameters for each magnetometer, we utilize a spherical calibration coil array. In our previous study, the position and orientation of each magnetometer were determined as the solution of an inverse problem through a numerical search that minimized the difference between the theoretical magnetic field signals from each coil and the measured signals detected by the magnetometer. In this study, we applied a deep neural network to estimate the position and orientation of each magnetometer in the helmet-shaped sensor array without solving the inverse problem. A total of 223 million pairs of a given magnetometer's five parameters (x, y, z, θ, and ϕ) and the corresponding theoretical magnetic field signals from the coils were used to train the neural network. The training process required approximately 53 h using a commercially available GPU-equipped computer. The trained neural network was then applied to acquire the sensor geometry from magnetic field data obtained during a conventional calibration procedure for a 160-channel whole-head magnetoencephalograph system using a spherical calibration coil array. The position and orientation of each magnetometer estimated by this method deviated by an average of 0.65 mm and 0.51°, respectively, from those obtained via the conventional inverse problem approach. The acquisition of the geometry for all 160 magnetometers required less than 8 ms. With such high-speed acquisition, this approach opens possibilities for future applications in acquiring positional information of wearable sensor arrays whose structures change in real time.
期刊介绍:
IEEE Magnetics Letters is a peer-reviewed, archival journal covering the physics and engineering of magnetism, magnetic materials, applied magnetics, design and application of magnetic devices, bio-magnetics, magneto-electronics, and spin electronics. IEEE Magnetics Letters publishes short, scholarly articles of substantial current interest.
IEEE Magnetics Letters is a hybrid Open Access (OA) journal. For a fee, authors have the option making their articles freely available to all, including non-subscribers. OA articles are identified as Open Access.