Minimax-optimal decoding of movement goals from local field potentials using complex spectral features

Detection of latent brain states from baseline neural activity in the amygdala

The amygdala responds to a large variety of socially and emotionally salient environmental and interoceptive stimuli. The context in which these stimuli occur determines their social and emotional significance. In canonical neurophysiological studies, the fast-paced succession of stimuli and events induce phasic changes in neural activity. During inter-trial intervals neural activity is expected to return to a stable and relatively featureless baseline. Context, such as the presence of a social partner, or the similarity of trials in a blocked design, induces brain states that can transcend the fast-paced succession of stimuli and can be recovered from the baseline firing rate of neurons. Indeed, the baseline firing rates of neurons in the amygdala change between blocks of trials of gentle grooming touch, delivered by a trusted social partner, and non-social airflow stimuli, delivered by a computer-controlled air valve. In this experimental paradigm, the presence of the groomer alone was sufficient to induce small but significant changes in baseline firing rates. Here, we examine local field potentials (LFP) recorded during these baseline periods to determine whether context was encoded by network dynamics that emerge in the local field potentials from the activity of large ensembles of neurons. We found that machine learning techniques can reliably decode social vs. non-social context from spectrograms of baseline local field potentials. Notably, decoding accuracy improved significantly with access to broad-band information. No significant differences were detected between the nuclei of the amygdala that receive direct or indirect inputs from areas of the prefrontal cortex known to coordinate flexible, context-dependent behaviors. The lack of nuclear specificity suggests that context-related synaptic inputs arise from a shared source, possibly interoceptive inputs that signal the sympathetic- vs. parasympathetic-dominated states characterizing non-social and social blocks, respectively.

The relationship between frequency content and representational dynamics in the decoding of neurophysiological data

Decoding of high temporal resolution, stimulus-evoked neurophysiological data is increasingly used to test theories about how the brain processes information. However, a fundamental relationship between the frequency spectra of the neural signal and the subsequent decoding accuracy timecourse is not widely recognised. We show that, in commonly used instantaneous signal decoding paradigms, each sinusoidal component of the evoked response is translated to double its original frequency in the subsequent decoding accuracy timecourses. We therefore recommend, where researchers use instantaneous signal decoding paradigms, that more aggressive low pass filtering is applied with a cut-off at one quarter of the sampling rate, to eliminate representational alias artefacts. However, this does not negate the accompanying interpretational challenges. We show that these can be resolved by decoding paradigms that utilise both a signal's instantaneous magnitude and its local gradient information as features for decoding. On a publicly available MEG dataset, this results in decoding accuracy metrics that are higher, more stable over time, and free of the technical and interpretational challenges previously characterised. We anticipate that a broader awareness of these fundamental relationships will enable stronger interpretations of decoding results by linking them more clearly to the underlying signal characteristics that drive them.

High Classification Accuracy of Touch Locations from S1 LFPs Using CNNs and Fastai

The primary somatosensory cortex (S1) is a region often targeted for input via somatosensory neuroprosthesis as tactile and proprioception are represented in S1. How this information is represented is an ongoing area of research. Neural signals are high-dimensional, making accurate models for decoding a significant challenge. Artificial neural networks (ANNs) have proven efficient at classification tasks in multiple fields. Moreover, ANNs allow for transfer learning, which exploits feature extraction trained on a large and more general dataset than may be available for a particular problem. In this work, convolutional neural networks (CNN), used for image recognition, were fine-tuned with somatosensory cortical recordings during experiments with naturalistic touch stimuli. We created a highly accurate ( correct) classifier for cutaneous stimulation locations as part of a somatosensory neuroprosthesis pipeline. Here we present the classifier results. Clinical Relevance- Our work provides a method for classifying cortical activity in brain-machine interface applications, specifically towards somatosensory neuroprosthetics.

Deep Pinsker and James-Stein Neural Networks for Decoding Motor Intentions From Limited Data

Non-parametric regression has been shown to be useful in extracting relevant features from Local Field Potential (LFP) signals for decoding motor intentions. Yet, in many instances, brain-computer interfaces (BCIs) rely on simple classification methods, circumventing deep neural networks (DNNs) due to limited training data. This paper leverages the robustness of several important results in non-parametric regression to harness the potentials of deep learning in limited data setups. We consider a solution that combines Pinsker's theorem as well as its adaptively optimal counterpart due to James-Stein for feature extraction from LFPs, followed by a DNN for classifying motor intentions. We apply our approach to the problem of decoding eye movement intentions from LFPs collected in macaque cortex while the animals perform memory-guided visual saccades to one of eight target locations. The results demonstrate that a DNN classifier trained over the Pinsker features outperforms the benchmark method based on linear discriminant analysis (LDA) trained over the same features.

Predicting task performance from biomarkers of mental fatigue in global brain activity

Objective.

Detection and early prediction of mental fatigue (i.e. shifts in vigilance), could be used to adapt neuromodulation strategies to effectively treat patients suffering from brain injury and other indications with prominent chronic mental fatigue.

Approach.

In this study, we analyzed electrocorticography (ECoG) signals chronically recorded from two healthy non-human primates (NHP) as they performed a sustained attention task over extended periods of time. We employed a set of spectrotemporal and connectivity biomarkers of the ECoG signals to identify periods of mental fatigue and a gradient boosting classifier to predict performance, up to several seconds prior to the behavioral response.

Main results.

Wavelet entropy and the instantaneous amplitude and frequency were among the best single features across sessions in both NHPs. The classification performance using higher order spectral-temporal (HOST) features was significantly higher than that of conventional spectral power features in both NHPs. Across the 99 sessions analyzed, average F1 scores of 77.5%±8.2% and 91.2%±3.6%, and accuracy of 79.5%±8.9% and 87.6%±3.9 % for the classifier were obtained for each animal, respectively.

Significance.

Our results here demonstrate the feasibility of predicting performance and detecting periods of mental fatigue by analyzing ECoG signals, and that this general approach, in principle, could be used for closed-loop control of neuromodulation strategies.

Human stereoEEG recordings reveal network dynamics of decision-making in a rule-switching task

The processing steps that lead up to a decision, i.e., the transformation of sensory evidence into motor output, are not fully understood. Here, we combine stereoEEG recordings from the human cortex, with single-lead and time-resolved decoding, using a wide range of temporal frequencies, to characterize decision processing during a rule-switching task. Our data reveal the contribution of rostral inferior parietal lobule (IPL) regions, in particular PFt, and the parietal opercular regions in decision processing and demonstrate that the network representing the decision is common to both task rules. We reconstruct the sequence in which regions engage in decision processing on single trials, thereby providing a detailed picture of the network dynamics involved in decision-making. The reconstructed timeline suggests that the supramarginal gyrus in IPL links decision regions in prefrontal cortex with premotor regions, where the motor plan for the response is elaborated.

Cross-subject decoding of eye movement goals from local field potentials

OBJECTIVE

We consider the cross-subject decoding problem from local field potential (LFP) signals, where training data collected from the prefrontal cortex (PFC) of a source subject is used to decode intended motor actions in a destination subject.

APPROACH

We propose a novel supervised transfer learning technique, referred to as data centering, which is used to adapt the feature space of the source to the feature space of the destination. The key ingredients of data centering are the transfer functions used to model the deterministic component of the relationship between the source and destination feature spaces. We propose an efficient data-driven estimation approach for linear transfer functions that uses the first and second order moments of the class-conditional distributions.

MAIN RESULTS

We apply our data centering technique with linear transfer functions for cross-subject decoding of eye movement intentions in an experiment where two macaque monkeys perform memory-guided visual saccades to one of eight target locations. The results show peak cross-subject decoding performance of [Formula: see text], which marks a substantial improvement over random choice decoder. In addition to this, data centering also outperforms standard sampling-based methods in setups with imbalanced training data.

SIGNIFICANCE

The analyses presented herein demonstrate that the proposed data centering is a viable novel technique for reliable LFP-based cross-subject brain-computer interfacing and neural prostheses.