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 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 hours 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 the 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 degree, 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.

An adjustable helmet-style magnetoresistive (MR) sensor array, a room-temperature magnetic flux sensor, was developed to demonstrate simultaneous multipoint measurement of the somatosensory evoked magnetic field (SEF). The SEF was measured in three healthy subjects using an array of 30-channel MR sensors placed on the left hemisphere of the head with median nerve stimulation in the right wrist and averaged over 8,000 measurements. An M20 component (maximum amplitude of 725 ± 257 fT, peak latency of 20.5 ± 0.45 ms), considered to originate from the primary somatosensory cortex, was observed at an approximate latency of 20 ms of the magnetic field waveform in all cases. The phase inversion observed around C3 corresponded to the palmar area of the primary somatosensory cortex on the contour map of the magnetic field at the M20 peak. The MR sensor, a relatively inexpensive and easy-to-use magnetic sensor that does not require a zero-field environment, was successfully used for simultaneous multipoint SEF measurements in humans and may be a promising option to realize a reasonable magnetoencephalography application device.