With real-time clustered multiple signal classification (RTC-MUSIC) we present a real-time source localization algorithm, which can handle low SNRs and can reduce the computational effort. It provides correlation information together with sparse source estimation results, which can, e.g., be used to identify evoked responses with high sensitivity. RTC-MUSIC clusters the forward solution based on an anatomical brain atlas and optimizes the scanning process inherent to MUSIC approaches. Publisher’s Version

Publication on RTC-MUSIC

We are excited to present the newest feature of MNE-CPP: Real-Time capable visualization of EEG/MEG sensor data. During a student project several new key features were implemented, which are described below. First a method to project sensors to the mesh, which is to be interpolated on, was implemented.  The projection is needed because sensor positions may be somewhat above the vertices of the used mesh. In order to interpolate signals, […]

Visualization of EEG/MEG Sensor Data

In the latest release (MNE-CPP v1.0.0-beta 3.0) we incorporated a technical preview of MNE Deep a deep learning library which facilitates Microsoft’s CNTK. CNTK is a framework which allows to analyze and reveal relations in massive datasets through deep learning by providing uncompromised scaling, speed and accuracy. The new MNE Deep library is used in the Brain Inside Out (BIO) project for modeling of brain structures with deep neuronal networks. MNE Deep also […]

Deep Learning with MNE-CPP

Magnetoencephalography (MEG) and Electroencephalography (EEG) provides high temporal resolution which allows a detailed investigation of time related neuronal activation properties. In real-time analysis two major challenges have to be handled: the low signal-to-noise ratio (SNR) and the limited time available for computations. We recently proposed Real-Time Clustered Multiple Signal Classification (RTC-MUSIC) as a real-time source localization algorithm, which can handle low SNRs and can cope with the high computational effort. It […]

RTC-MUSIC: Real-Time Source Localization

Together with our partners at the Boston Children’s Hospital (Harvad Medical School) we provided the software MNE Scan to acquire and process data from the novel BabyMEG system in real-time. The BabyMEG is a wohle head pediatric MEG system, which is able to measure kids up to three years of age. The BabyMEG is equipped with 270 inner layer magnetometers and 35×3-axis outer layer sensors. By using a recycling system, […]

BabyMEG: Real-Time Data Processing

In the past months the MNE-CPP team has been improving the disp3D library and adding new features for better data visualization. The recent release of Qt 5.7 brought much anticipated updates and new modules into the field. QtCharts module was implemented for data analysis in the form of distribution histogram. This will show the distribution of EEG and MEG data. In addition, users will now be able to effortlessly hide […]

New 3D Visualization Features

RAP-MUSIC Algorithm GPU (CUDA 4.0) implementation is finished. To realize RAP-MUSIC real-time source localization we reduce in a first step the computational costs by modifying and pre-calculating components of the subspace correlation. In a second step we apply to the accelerated algorithm a modified Powell’s Conjugate Gradient Method, which highly optimizes the search process. Since the subspace correlations of the RAP-MUSIC algorithm are independent, they are predestined to be computed […]

RAP-MUSIC GPU Implementation