Decoding Kinematic Information From Primary Motor Cortex Ensemble Activities Using a Deep Canonical Correlation Analysis

Dynamical flexible inference of nonlinear latent factors and structures in neural population activity

Modelling the spatiotemporal dynamics in the activity of neural populations while also enabling their flexible inference is hindered by the complexity and noisiness of neural observations. Here we show that the lower-dimensional nonlinear latent factors and latent structures can be computationally modelled in a manner that allows for flexible inference causally, non-causally and in the presence of missing neural observations. To enable flexible inference, we developed a neural network that separates the model into jointly trained manifold and dynamic latent factors such that nonlinearity is captured through the manifold factors and the dynamics can be modelled in tractable linear form on this nonlinear manifold. We show that the model, which we named 'DFINE' (for 'dynamical flexible inference for nonlinear embeddings') achieves flexible inference in simulations of nonlinear dynamics and across neural datasets representing a diversity of brain regions and behaviours. Compared with earlier neural-network models, DFINE enables flexible inference, better predicts neural activity and behaviour, and better captures the latent neural manifold structure. DFINE may advance the development of neurotechnology and investigations in neuroscience.

Finding Kinematics-Driven Latent Neural States From Neuronal Population Activity for Motor Decoding

While intracortical brain-machine interfaces (BMIs) demonstrate feasibility to restore mobility to people with paralysis, it is still challenging to maintain high-performance decoding in clinical BMIs. One of the main obstacles for high-performance BMI is the noise-prone nature of traditional decoding methods that connect neural response explicitly with physical quantity, such as velocity. In contrast, the recent development of latent neural state model enables a robust readout of large-scale neuronal population activity contents. However, these latent neural states do not necessarily contain kinematic information useful for decoding. Therefore, this study proposes a new approach to finding kinematics-dependent latent factors by extracting latent factors' kinematics-dependent components using linear regression. We estimated these components from the population activity through nonlinear mapping. The proposed kinematics-dependent latent factors generate neural trajectories that discriminate latent neural states before and after the motion onset. We compared the decoding performance of the proposed analysis model with the results from other popular models. They are factor analysis (FA), Gaussian process factor analysis (GPFA), latent factor analysis via dynamical systems (LFADS), preferential subspace identification (PSID), and neuronal population firing rates. The proposed analysis model results in higher decoding accuracy than do the others ( % improvement on average). Our approach may pave a new way to extract latent neural states specific to kinematic information from motor cortices, potentially improving decoding performance for online intracortical BMIs.

Corticomuscular coupling analysis based on improved LSTM and transfer entropy

The study of functional corticomuscular coupling can reflect the interaction between the cerebral cortex and muscle tissue, thereby helping to understand how the brain controls muscle tissue and the effect of muscle movement on brain function. This study proposes a detection model of the coupling strength between the cortex and muscles. The detection model uses an adaptive selector to choose the optimal long short-term memory network, uses this network to extract the features of electroencephalography and electromyography, and finally transforms time characteristics into the frequency domain. The transfer entropy is used to represent the interaction intensity of signals in different frequency bands. Using this model, we analyze the coupling relationship between the cortex and muscles in the three movements of wrist flexion, wrist extension, and clench fist, and compare the model with traditional wavelet coherence analysis and deep canonical correlation analysis. The experimental results show that our model can not only express the bidirectional coupling relationship between different frequency bands but also suppress the possible false coupling that traditional methods may detect. Our research shows that the proposed model has great potential in medical rehabilitation, movement decoding, and other fields.