Selective peripheral nerve recordings from nerve cuff electrodes using convolutional neural networks.

OBJECTIVE: Recording and stimulating from the peripheral nervous system are becoming important components in a new generation of bioelectronics systems. Although neurostimulation has seen a history of successful chronic applications in humans, peripheral nerve recording in humans chronically remains a challenge. Multi-contact nerve cuff electrode configurations have the potential to improve recording selectivity. We introduce the idea of using a convolutional neural network (CNN) to associate recordings of individual naturally evoked compound action potentials (CAPs) with neural pathways of interest, by exploiting the spatiotemporal patterns in multi-contact nerve cuff recordings. APPROACH: Nine Long-Evan rats were implanted with a 56-channel nerve cuff electrode on the sciatic nerve and afferent activity was selectively evoked in different fascicles (tibial, peroneal, sural) using mechanical stimuli. A recurrent neural network was then used to predict joint angles based on the predicted firing patterns from the CNN. Performance was measured based on the classification accuracy, F 1-score and the ability to track the ankle joint angle. MAIN RESULTS: Classification accuracy and F 1-score of the best CNN configuration were [Formula: see text] and 0.747 ± 0.114, respectively. The mean Pearson correlation coefficient between the manually measured ankle angle and the angle predicted from the estimated firing rate was [Formula: see text] Significance. The proposed method demonstrates that CAP-based classification can be achieved with high accuracy and can be used to track a physiological meaningful measure (e.g. joint angle). These results provide a promising direction for realizing more effective and intuitive neuroprosthetic systems.

Classification of naturally evoked compound action potentials in peripheral nerve spatiotemporal recordings.

Peripheral neural signals have the potential to provide the necessary motor, sensory or autonomic information for robust control in many neuroprosthetic and neuromodulation applications. However, developing methods to recover information encoded in these signals is a significant challenge. We introduce the idea of using spatiotemporal signatures extracted from multi-contact nerve cuff electrode recordings to classify naturally evoked compound action potentials (CAP). 9 Long-Evan rats were implanted with a 56-channel nerve cuff on the sciatic nerve. Afferent activity was selectively evoked in the different fascicles of the sciatic nerve (tibial, peroneal, sural) using mechano-sensory stimuli. Spatiotemporal signatures of recorded CAPs were used to train three different classifiers. Performance was measured based on the classification accuracy, F1-score, and the ability to reconstruct original firing rates of neural pathways. The mean classification accuracies, for a 3-class problem, for the best performing classifier was 0.686 ± 0.126 and corresponding mean F1-score was 0.605 ± 0.212. The mean Pearson correlation coefficients between the original firing rates and estimated firing rates found for the best classifier was 0.728 ± 0.276. The proposed method demonstrates the possibility of classifying individual naturally evoked CAPs in peripheral neural signals recorded from extraneural electrodes, allowing for more precise control signals in neuroprosthetic applications.

The Impact of Anisotropy on the Accuracy of Conductivity Imaging: A Quantitative Validation Study.

We present a quantitative validation study to assess the accuracy of low-frequency conductivity imaging methods, based on a testing current measured using Current Density Imaging (CDI). We tested the proposed procedure to study the influence of tissue anisotropy on the accuracy of conductivity reconstruction methods, using a finite element model of anisotropic brain tissue. Simulations were carried out for three different levels of tissue anisotropy to compare the results obtained by our recently developed anisotropic conductivity method with those obtained by our well-established conductivity method that assumes isotropic conductivity. The validation results clearly show that the conductivity imaging method which takes into account tissue anisotropy yields significantly superior accuracy.

Use of spatiotemporal templates for pathway discrimination in peripheral nerve recordings: a simulation study.

OBJECTIVE: Extraction of information from the peripheral nervous system can provide control signals in neuroprosthetic applications. However, the ability to selectively record from different pathways within peripheral nerves is limited. We investigated the integration of spatial and temporal information for pathway discrimination in peripheral nerves using measurements from a multi-contact nerve cuff electrode. APPROACH: Spatiotemporal templates were established for different neural pathways of interest, and used to obtain tailored matched filters for each of these pathways. Simulated measurements of compound action potentials propagating through the nerve in different test cases were used to evaluate classification accuracy, percentage of missed spikes, and ability to reconstruct the original firing rates of the neural pathways. MAIN RESULTS: The mean Pearson correlation coefficients between the original firing rates and estimated firing rates over all tests cases was found to be 0.832 ± 0.161, 0.421 ± 0.145, 0.481 ± 0.340 for our algorithm, Bayesian spatial filters, and velocity selective recordings respectively. SIGNIFICANCE: The proposed method shows that the spatiotemporal templates were able to provide more robust spike detection and reliable pathway discrimination than these existing algorithms.

Experimental implementation of a new method of imaging anisotropic electric conductivities.

This paper presents the first experiment of imaging anisotropic impedance using a novel technique called Diffusion Tensor Current Density Impedance Imaging (DTCD-II). A biological anisotropic tissue phantom was constructed and an experimental implementation of the new method was performed. The results show that DT-CD-II is an effective way of non-invasively measuring anisotropic conductivity in biological media. The cross-property factor between the diffusion tensor and the conductivity tensor has been carefully determined from the experimental data, and shown to be spatially inhomogeneous. The results show that this novel imaging approach has the potential to provide valuable new information on tissue properties.

Radio-frequency current density imaging based on a 180 (°) sample rotation with feasibility study of full current density vector reconstruction.

Radio-frequency current density imaging (RF-CDI) is a technique that noninvasively measures current density distributions at the Larmor frequency utilizing magnetic resonance imaging. Previously implemented RF-CDI methods reconstruct the applied current density component J(z) along the static magnetic field of the imager [(B)\vec](0) (the z direction) based on the assumption that the z-directional change of the magnetic field component H(z) can be ignored compared to J(z). However, this condition may be easily violated in biomedical applications. We propose a new reconstruction method for RF-CDI, which does not rely on the aforementioned assumption. Instead, the sample is rotated by 180 (°) in the horizontal plane to collect magnetic resonance data from two opposite positions. Using simulations and experiments, we have verified that this approach can fully recover one component of current density. Furthermore, this approach can be extended to measure three dimensional current density vectors by one additional sample orientation in the horizontal plane. We have therefore demonstrated for the first time the feasibility of imaging the magnitude and phase of all components of a radio-frequency current density vector field.

Polar decomposition radio-frequency current density imaging.

Polar Decomposition Radio-frequency Current Density Imaging (PD-RFCDI) is an imaging technique that non-invasively measures RF current density components inside a sample using MRI. Previous PD-RFCDI implementations suffer from the strict constraint on the amount of applied current as well as severe interference from the unwanted induced current. This work proposes solutions to both problems which successfully remove the current constraints of PD-RFCDI. Both simulation and experiment were used to verify the validity of PD-RFCDI on a clinical MRI scanner.

Multislice radio-frequency current density imaging.

Radio-frequency current density imaging (RF-CDI) is an imaging technique that noninvasively measures current density distribution at the Larmor frequency utilizing magnetic resonance imaging (MRI). Previously implemented RF-CDI techniques were only able to image a single slice transverse to the static magnetic field B(0) . This paper describes the first realization of a multislice RF-CDI sequence on a 1.5 T clinical imager. Multislice RF current density images have been reconstructed for two phantoms. The influence of MRI random noise on the sensitivity of the multislice RF-CDI measurement has also been studied by theoretical analysis, simulation and phantom experiments.

Current density impedance imaging.

Current density impedance imaging (CDII) is a new impedance imaging technique that can noninvasively measure the conductivity distribution inside a medium. It utilizes current density vector measurements which can be made using a magnetic resonance imager (MRI) (Scott , 1991). CDII is based on a simple mathematical expression for inverted Delta sigma / sigma = inverted Delta ln sigma, the gradient of the logarithm of the conductivity sigma, at each point in a region where two current density vectors J1 and J2 have been measured and J1 x J2 not equal 0. From the calculated inverted Delta ln sigma and a priori knowledge of the conductivity at the boundary, the logarithm of the conductivity ln sigma is integrated by two different methods to produce an image of the conductivity sigma in the region of interest. The CDII technique was tested on three different conductivity phantoms. Much emphasis has been placed on the experimental validation of CDII results against direct bench measurements by commercial LCR meters before and after CDII was performed.

Noise analysis for multi-slice radio frequency current density imaging.

Radio frequency current density imaging (RF-CDI) is an imaging technique that measures current density distribution at the Larmor frequency utilizing magnetic resonance imaging (MRI). The multi-slice RF-CDI sequence has extended the ability of RF-CDI to image multiple slices and thus has enhanced its capacity for biomedical applications. In this paper, the influence of MRI random noise on the sensitivity of multi-slice RF-CDI measurement is studied. The formula of current noise is derived, which is verified by both simulation and phantom experiments. A 3-D finite-difference time-domain (FDTD) model is employed to compute the electromagnetic fields in the simulation.

Comparison of current densities measured in a pig heart during states of ventricular fibrillation and post-mortem for different defibrillation electrode positions.

Current density imaging (CDI) is an MRI technique used to quantitatively measure current density vectors in biological tissue. A fast CDI sequence was developed that can image the whole body of a 4 kg pig in about 15 minutes. A state of ventricular fibrillation (VF) can be sustained for nearly 30 minutes allowing two complete CDI scans of the same subject. A single parameter, i.e. electrode position, is adjusted between the two scans for comparative analysis. This study compares the current density vector directions and current density magnitudes measured for two typical electrode positions, i.e. apex anterior (AA) and apex posterior (AP). The comparative experiment is repeated on the same subjects for states of immediate post-mortem and one hour post-mortem. Further, the acquired vector datasets are used to compute conductivity images of the heart.