BCIwiki — Brain-computer interface news, research and industry database

A study published in Computers in biology and medicine introduces LEGEND, a neural-decoding architecture that jointly models cortical EEG, spinal ESG, and peripheral-muscle EMG for a neural bypass in spinal cord injury rehabilitation. The model encodes the three signal modalities in Lorentz hyperbolic space, connects 51 channel nodes through a signed tri-layer phase-locking-value graph, and refines the representation with graph attention. Under strict leave-one-subject-out evaluation on the Steele dataset, LEGEND achieved 56.51%±12.27% accuracy, 23.4 percentage points above EEGNet. The researchers argue that hyperbolic representations can capture complex relationships across the motor hierarchy, providing a computational foundation for rehabilitation decoding that links brain, spinal, and muscle activity.

The FDA cleared the Ceribell Neurology Review Software on June 24, 2026, finding it substantially equivalent under submission number K260998 through the traditional 510(k) pathway. The agency classifies it as Automatic Event Detection Software for Full-Montage Electroencephalograph, a Class II device under regulation 882.1400, with neurology as the assigned review panel. The category covers software that automatically flags events within full-montage EEG recordings, surfacing candidate segments from long records for clinician review.

The trial compares motor imagery BCI plus standard rehabilitation against standard rehabilitation alone in stroke patients with hemiplegia, tracking limb motor function and daily living ability. It planned to enroll 60 participants, 30 per arm, with the first participant enrolled on August 10, 2022; the registry now lists the study as completed. Beyond motor scales, the primary outcomes include functional connectivity and a lateralization index measured with fNIRS, probing brain-network changes rather than behavior scores alone.

Researchers in the Department of Brain Sciences at Israel's Weizmann Institute of Science developed BAMBI, a brain-computer interface that uses a head-mounted miniature microscope to image calcium signals from active neurons in real time and deliver feedback. Because it realigns to the same field of view in each session, it tracks the same group of neurons over multiple days without retraining. Tested in head-fixed and freely moving mice across different behavioral paradigms, the animals learned to stably modulate specific hippocampal neurons for rewards over several days.

Using implantable brain-machine interface (iBMI) data from a non-human primate two-dimensional finger task, the study tests whether brain-muscle synergies improve decoding performance and generalization. Principal component analysis (PCA), demixed PCA (dPCA) and non-negative matrix factorization (NMF) all compressed brain-muscle data effectively with minimal decoding-accuracy loss, but none improved performance through denoising or enhanced cross-task generalization. The authors conclude that extracting synergies alone does not yield a better or cleaner control space for linear decoding, and call for larger samples and more muscle channels.

Researchers at Lanzhou University, Zhejiang University, the University of Hong Kong and Sun Yat-sen University have built MindShow, a unified generative framework that reconstructs images from fMRI at cohort level rather than one subject at a time. A hierarchically conditioned mixture-of-experts encoder separates population-shared latent representations from subject-specific neural traits, so a new subject can be adapted with limited calibration data; a gated Perceiver bottleneck maps fMRI features into fixed-size image and text tokens, an optimal transport loss aligns them with a pretrained vision-language model, and a frozen diffusion model renders the image. The authors report better high-level reconstruction metrics with competitive structural fidelity, in a study published in Medical Image Analysis on June 20, 2026.

OYMotion and MicroPort NeuroScientific signed a strategic cooperation agreement on May 28, 2026 to jointly develop an interventional brain-computer interface rehabilitation system. The first product will be a multi-channel endovascular BCI that threads a signal-recording stent through the blood vessels to a target brain region, capturing intracranial electrical activity without opening the skull. MicroPort NeuroScientific will build the BCI system as a whole and OYMotion the limb side, with the pair targeting medical rehabilitation and human-machine interaction.

8 Chinese ministries jointly issued a policy document explicitly promoting the integration of AI with brain-computer interface, AR, VR, and MR technologies.

A study published in Computers in biology and medicine proposes dynamic wavelet-basis selection to improve non-invasive EEG imagined-speech classification. For each EEG epoch, the method minimizes wavelet entropy to select an informative basis and then injects Gaussian noise into the corresponding coefficients. A convolutional neural network with channel-wise excitation classifies the augmented signals. The dataset contains 32 channels, 8 stimuli, and recordings from 10 participants. The words-vowels combination reached a highest classification accuracy of 98% with a Cohen's kappa of 0.95, although performance was lower for the full class set. The researchers report that the method outperformed conventional augmentation strategies and static wavelet approaches, offering an adaptive way to address noise and non-stationarity in EEG decoding.

Neuracle Medical Technology (Shanghai) Co., Ltd. registered an Implantable EEG Electrode Kit in the NMPA Medical Device Unique Identification database. The model is K1014-15, and the registration certificate number is 国械注准20263120536. The listed kit includes a cortical electrode, a blank electrode, and surgical and fixation components. It is both a product with its own registration certificate and a component of an implantable brain-computer interface hand motor function compensation system. The system also includes an implant, an EEG transceiver, a pneumatic glove device, and software. This entry identifies the product and its composition; it does not establish the complete system's registration status or clinical performance.