Ensemble fractional sensitivity: a quantitative approach to neuron selection for decoding motor tasks

Comparing offline decoding performance in physiologically defined neuronal classes

Objective

Recently, several studies have documented the presence of a bimodal distribution of spike waveform widths in primary motor cortex. Although narrow and wide spiking neurons, corresponding to the two modes of the distribution, exhibit different response properties, it remains unknown if these differences give rise to differential decoding performance between these two classes of cells.

Approach

We used a Gaussian mixture model to classify neurons into narrow and wide physiological classes. Using similar-size, random samples of neurons from these two physiological classes, we trained offline decoding models to predict a variety of movement features. We compared offline decoding performance between these two physiologically defined populations of cells.

Main results

We found that narrow spiking neural ensembles decode motor parameters better than wide spiking neural ensembles including kinematics, kinetics, and muscle activity.

Significance

These findings suggest that the utility of neural ensembles in brain machine interfaces may be predicted from their spike waveform widths.

Tracking Neural Modulation Depth by Dual Sequential Monte Carlo Estimation on Point Processes for Brain-Machine Interfaces

Classic brain-machine interface (BMI) approaches decode neural signals from the brain responsible for achieving specific motor movements, which subsequently command prosthetic devices. Brain activities adaptively change during the control of the neuroprosthesis in BMIs, where the alteration of the preferred direction and the modulation of the gain depth are observed. The static neural tuning models have been limited by fixed codes, resulting in a decay of decoding performance over the course of the movement and subsequent instability in motor performance. To achieve stable performance, we propose a dual sequential Monte Carlo adaptive point process method, which models and decodes the gradually changing modulation depth of individual neuron over the course of a movement. We use multichannel neural spike trains from the primary motor cortex of a monkey trained to perform a target pursuit task using a joystick. Our results show that our computational approach successfully tracks the neural modulation depth over time with better goodness-of-fit than classic static neural tuning models, resulting in smaller errors between the true kinematics and the estimations in both simulated and real data. Our novel decoding approach suggests that the brain may employ such strategies to achieve stable motor output, i.e., plastic neural tuning is a feature of neural systems. BMI users may benefit from this adaptive algorithm to achieve more complex and controlled movement outcomes.

Advancing brain-machine interfaces: moving beyond linear state space models

Advances in recent years have dramatically improved output control by Brain-Machine Interfaces (BMIs). Such devices nevertheless remain robotic and limited in their movements compared to normal human motor performance. Most current BMIs rely on transforming recorded neural activity to a linear state space composed of a set number of fixed degrees of freedom. Here we consider a variety of ways in which BMI design might be advanced further by applying non-linear dynamics observed in normal motor behavior. We consider (i) the dynamic range and precision of natural movements, (ii) differences between cortical activity and actual body movement, (iii) kinematic and muscular synergies, and (iv) the implications of large neuronal populations. We advance the hypothesis that a given population of recorded neurons may transmit more useful information than can be captured by a single, linear model across all movement phases and contexts. We argue that incorporating these various non-linear characteristics will be an important next step in advancing BMIs to more closely match natural motor performance.

A systematic approach to selecting task relevant neurons

BACKGROUND

Since task related neurons cannot be specifically targeted during surgery, a critical decision to make is to select which neurons are task-related when performing data analysis. Including neurons unrelated to the task degrade decoding accuracy and confound neurophysiological results. Traditionally, task-related neurons are selected as those with significant changes in firing rate when a stimulus is applied. However, this assumes that neurons' encoding of stimuli are dominated by their firing rate with little regard to temporal dynamics.

NEW METHOD

This paper proposes a systematic approach for neuron selection, which uses a likelihood ratio test to capture the contribution of stimulus to spiking activity while taking into account task-irrelevant intrinsic dynamics that affect firing rates. This approach is denoted as the model deterioration excluding stimulus (MDES) test.

RESULTS

MDES is compared to firing rate selection in four case studies: a simulation, a decoding example, and two neurophysiology examples.

COMPARISON WITH EXISTING METHODS

The MDES rankings in the simulation match closely with ideal rankings, while firing rate rankings are skewed by task-irrelevant parameters. For decoding, 95% accuracy is achieved using the top 8 MDES-ranked neurons, while the top 12 firing-rate ranked neurons are needed. In the neurophysiological examples, MDES matches published results when firing rates do encode salient stimulus information, and uncovers oscillatory modulations in task-related neurons that are not captured when neurons are selected using firing rates.

CONCLUSIONS

These case studies illustrate the importance of accounting for intrinsic dynamics when selecting task-related neurons and following the MDES approach accomplishes that. MDES selects neurons that encode task-related information irrespective of these intrinsic dynamics which can bias firing rate based selection.

Modulation depth estimation and variable selection in state-space models for neural interfaces

Rapid developments in neural interface technology are making it possible to record increasingly large signal sets of neural activity. Various factors such as asymmetrical information distribution and across-channel redundancy may, however, limit the benefit of high-dimensional signal sets, and the increased computational complexity may not yield corresponding improvement in system performance. High-dimensional system models may also lead to overfitting and lack of generalizability. To address these issues, we present a generalized modulation depth measure using the state-space framework that quantifies the tuning of a neural signal channel to relevant behavioral covariates. For a dynamical system, we develop computationally efficient procedures for estimating modulation depth from multivariate data. We show that this measure can be used to rank neural signals and select an optimal channel subset for inclusion in the neural decoding algorithm. We present a scheme for choosing the optimal subset based on model order selection criteria. We apply this method to neuronal ensemble spike-rate decoding in neural interfaces, using our framework to relate motor cortical activity with intended movement kinematics. With offline analysis of intracortical motor imagery data obtained from individuals with tetraplegia using the BrainGate neural interface, we demonstrate that our variable selection scheme is useful for identifying and ranking the most information-rich neural signals. We demonstrate that our approach offers several orders of magnitude lower complexity but virtually identical decoding performance compared to greedy search and other selection schemes. Our statistical analysis shows that the modulation depth of human motor cortical single-unit signals is well characterized by the generalized Pareto distribution. Our variable selection scheme has wide applicability in problems involving multisensor signal modeling and estimation in biomedical engineering systems.

Neuron selection based on deflection coefficient maximization for the neural decoding of dexterous finger movements

Future generations of brain-machine interface (BMI) will require more dexterous motion control such as hand and finger movements. Since a population of neurons in the primary motor cortex (M1) area is correlated with finger movements, neural activities recorded in M1 area are used to reconstruct an intended finger movement. In a BMI system, decoding discrete finger movements from a large number of input neurons does not guarantee a higher decoding accuracy in spite of the increase in computational burden. Hence, we hypothesize that selecting neurons important for coding dexterous flexion/extension of finger movements would improve the BMI performance. In this paper, two metrics are presented to quantitatively measure the importance of each neuron based on Bayes risk minimization and deflection coefficient maximization in a statistical decision problem. Since motor cortical neurons are active with movements of several different fingers, the proposed method is more suitable for a discrete decoding of flexion-extension finger movements than the previous methods for decoding reaching movements. In particular, the proposed metrics yielded high decoding accuracies across all subjects and also in the case of including six combined two-finger movements. While our data acquisition and analysis was done off-line and post processing, our results point to the significance of highly coding neurons in improving BMI performance.

Local-learning-based neuron selection for grasping gesture prediction in motor brain machine interfaces

OBJECTIVE

The high-dimensional neural recordings bring computational challenges to movement decoding in motor brain machine interfaces (mBMI), especially for portable applications. However, not all recorded neural activities relate to the execution of a certain movement task. This paper proposes to use a local-learning-based method to perform neuron selection for the gesture prediction in a reaching and grasping task.

APPROACH

Nonlinear neural activities are decomposed into a set of linear ones in a weighted feature space. A margin is defined to measure the distance between inter-class and intra-class neural patterns. The weights, reflecting the importance of neurons, are obtained by minimizing a margin-based exponential error function. To find the most dominant neurons in the task, 1-norm regularization is introduced to the objective function for sparse weights, where near-zero weights indicate irrelevant neurons.

MAIN RESULTS

The signals of only 10 neurons out of 70 selected by the proposed method could achieve over 95% of the full recording's decoding accuracy of gesture predictions, no matter which different decoding methods are used (support vector machine and K-nearest neighbor). The temporal activities of the selected neurons show visually distinguishable patterns associated with various hand states. Compared with other algorithms, the proposed method can better eliminate the irrelevant neurons with near-zero weights and provides the important neuron subset with the best decoding performance in statistics. The weights of important neurons converge usually within 10-20 iterations. In addition, we study the temporal and spatial variation of neuron importance along a period of one and a half months in the same task. A high decoding performance can be maintained by updating the neuron subset.

SIGNIFICANCE

The proposed algorithm effectively ascertains the neuronal importance without assuming any coding model and provides a high performance with different decoding models. It shows better robustness of identifying the important neurons with noisy signals presented. The low demand of computational resources which, reflected by the fast convergence, indicates the feasibility of the method applied in portable BMI systems. The ascertainment of the important neurons helps to inspect neural patterns visually associated with the movement task. The elimination of irrelevant neurons greatly reduces the computational burden of mBMI systems and maintains the performance with better robustness.

Mutual information analysis on non-stationary neuron importance for brain machine interfaces

Decoding with the important neuron subset has been widely used in brain machine interfaces (BMIs), as an effective strategy to reduce computational complexity. Previous works usually assume stationary of neuron importance, which may not be true according to recent research. We propose to conduct a mutual information evaluation to track the time-varying neuron importance over time. We found worth noting changes both in information amount and space distribution in our experiment. When the method is applied with a Kalman filter, the decoding performance achieve is better (with higher correlation coefficient) than when a fixed subset, which shows that time-varying neuron importance should be considered in adaptive algorithms.

Neuron Selection by Relative Importance for Neural Decoding of Dexterous Finger Prosthesis Control Application

Future generations of upper limb prosthesis will have dexterous hand with individual fingers and will be controlled directly by neural signals. Neurons from the primary motor (M1) cortex code for finger movements and provide the source for neural control of dexterous prosthesis. Each neuron's activation can be quantified by the change in firing rate before and after finger movement, and the quantified value is then represented by the neural activity over each trial for the intended movement. Since this neural activity varies with the intended movement, we define the relative importance of each neuron independent of specific intended movements. The relative importance of each neuron is determined by the inter-movement variance of the neural activities for respective intended movements. Neurons are ranked by the relative importance and then a subpopulation of rank-ordered neurons is selected for the neural decoding. The use of the proposed neuron selection method in individual finger movements improved decoding accuracy by 21.5% in the case of decoding with only 5 neurons and by 9.2% in the case of decoding with only 10 neurons. With only 15 highly-ranked neurons, a decoding accuracy of 99.5% was achieved. The performance improvement is still maintained when combined movements of two fingers were included though the decoding accuracy fell to 95.7%. Since the proposed neuron selection method can achieve the targeting accuracy of decoding algorithms with less number of input neurons, it can be significant for developing brain-machine interfaces for direct neural control of hand prostheses.

Sparse decoding of multiple spike trains for brain-machine interfaces

Brain-machine interfaces (BMIs) rely on decoding neuronal activity from a large number of electrodes. The implantation procedures, however, do not guarantee that all recorded units encode task-relevant information: selection of task-relevant neurons is critical to performance but is typically performed based on heuristics. Here, we describe an algorithm for decoding/classification of volitional actions from multiple spike trains, which automatically selects the relevant neurons. The method is based on sparse decomposition of the high-dimensional neuronal feature space, projecting it onto a low-dimensional space of codes serving as unique class labels. The new method is tested against a range of existing methods using simulations and recordings of the activity of 1592 neurons in 23 neurosurgical patients who performed motor or speech tasks. The parameter estimation algorithm is orders of magnitude faster than existing methods and achieves significantly higher accuracies for both simulations and human data, rendering sparse decoding highly attractive for BMIs.

Decoding dexterous finger movements in a neural prosthesis model approaching real-world conditions

Dexterous finger movements can be decoded from neuronal action potentials acquired from a nonhuman primate using a chronically implanted Utah Electrode Array. We have developed an algorithm that can, after training, detect and classify individual and combined finger movements without any a priori knowledge of the data, task, or behavior. The algorithm is based on changes in the firing rates of individual neurons that are tuned for one or more finger movement types. Nine different movement types, which consisted of individual flexions, individual extensions, and combined flexions of the thumb, index finger, and middle finger, were decoded. The algorithm performed reliably on data recorded continuously during movement tasks, including a no-movement state, with an overall average sensitivity and specificity that were both > 92%. These results demonstrate a viable algorithm for decoding dexterous finger movements under conditions similar to those required for a real-world neural prosthetic application.

Neuron selection for decoding dexterous finger movements

Many brain machine interfaces (BMI) seek to use the activity from hundreds of simultaneously recorded neurons to reconstruct an individual's kinematics. However, many of these neurons are not task related since there is no way to surgically target those neurons. This causes model based decoding to suffer easily from over-fitting on noisy unrelated neurons. Previous methods, such as correlation analysis and sensitivity analysis, seek to select neurons based on which reduced order model best matches the ensemble model and thus does not worry about over fitting. To address this issue, this paper presents a new method, cross model validation, that ranks neuron importance on the neuron model's ability to generalize well to data from correct movements and poorly to data from incorrect movements. This method attempts to highlight the neurons that are able to distinguish between movements the best and decode accurately. Selecting neurons using cross model validation scores as opposed to randomly selecting them can increase decoding accuracy up to 2.5 times or by 44%. These results showcase the importance of neuron selection in decoding and the ability of cross model validation in discerning each neuron's utility in decoding.