SpikeDeeptector: a deep-learning based method for detection of neural spiking activity

Abstract

Objective. In electrophysiology, microelectrodes are the primary source for recording neural data (single unit activity). These microelectrodes can be implanted individually or in the form of arrays containing dozens to hundreds of channels. Recordings of some channels contain neural activity, which are often contaminated with noise. Another fraction of channels does not record any neural data, but only noise. By noise, we mean physiological activities unrelated to spiking, including technical artifacts and neural activities of neurons that are too far away from the electrode to be usefully processed. For further analysis, an automatic identification and continuous tracking of channels containing neural data is of great significance for many applications, e.g. automated selection of neural channels during online and offline spike sorting. Automated spike detection and sorting is also critical for online decoding in brain–computer interface (BCI) applications, in which only simple threshold crossing events are often considered for feature extraction. To our knowledge, there is no method that can universally and automatically identify channels containing neural data. In this study, we aim to identify and track channels containing neural data from implanted electrodes, automatically and more importantly universally. By universally, we mean across different recording technologies, different subjects and different brain areas. Approach. We propose a novel algorithm based on a new way of feature vector extraction and a deep learning method, which we call SpikeDeeptector. SpikeDeeptector considers a batch of waveforms to construct a single feature vector and enables contextual learning. The feature vectors are then fed to a deep learning method, which learns contextualized, temporal and spatial patterns, and classifies them as channels containing neural spike data or only noise. Main results. We trained the model of SpikeDeeptector on data recorded from a single tetraplegic patient with two Utah arrays implanted in different areas of the brain. The trained model was then evaluated on data collected from six epileptic patients implanted with depth electrodes, unseen data from the tetraplegic patient and data from another tetraplegic patient implanted with two Utah arrays. The cumulative evaluation accuracy was 97.20% on 1.56 million hand labeled test inputs. Significance. The results demonstrate that SpikeDeeptector generalizes not only to the new data, but also to different brain areas, subjects, and electrode types not used for training. Clinical trial registration number. The clinical trial registration number for patients implanted with the Utah array is NCT 01849822. For the epilepsy patients, approval from the local ethics committee at the Ruhr-University Bochum, Germany, was obtained prior to implantation.

An Accurate and Robust Method for Spike Sorting Based on Convolutional Neural Networks

“…A possible reason is that the 1D-CNN could not “learn” enough features from the limited spike sampling points. Secondly, as with other deep learning approaches [ 15 , 52 , 53 ], the number of labels in the training set was of great importance to the clustering accuracy. From the previous analysis of simulated data, it was found that the accuracy could reach over 99.5% when there were more than 60 training spikes of each cluster available in the “easy” datasets.…”

“…In fact, there are usually four main steps in conventional approaches for spike sorting: (1) Bandpass-filtering (e.g., 300–3000 Hz) the recorded raw data to eliminate the interferences of high-frequency noise and low-frequency field potential; (2) detecting the spikes by determining an amplitude threshold [ 14 ] or utilizing other improved methods [ 15 ], such as wavelet transforms [ 16 ] and fuzzy decision [ 2 ]; (3) extracting discriminative features from the detected spikes, frequently using approaches such as principal component analysis (PCA) [ 17 , 18 , 19 ] and wavelet transform coefficients [ 14 , 20 , 21 ]; (4) grouping the points in feature space to obtain clusters associated with individual neurons. Many classical and advanced methods have been adopted for this purpose, such as superparamagnetic clustering (SPC) [ 14 ], k-means clustering [ 22 ], and a mixture of Gaussians [ 23 , 24 ].…”

“…However, the method did not show better sorting performance on overlapped spikes. The SpikeDeeptector method employed a CNN to select meaningful channels for brain–computer interfaces [ 15 ]. It considered a batch of waveforms to construct a single feature vector, which were fed to a deep learning method.…”

Spike detection and sorting with deep learning

“…Machine learning was also successfully used to provide robust control of a deep brain stimulating device depending on real-time cortical signals [34]. An interesting application of convolutional networks can be found in [35]. The network presented in the paper (SpikeDeeptector) is used for detecting and tracing channels that actual signal can be recorded on, in contrast with the other ones, yielding only artifacts.…”

Deep Learning-Based Template Matching Spike Classification for Extracellular Recordings

“…Its application in the field of neural signal analysis can also be seen. SpikeDeeptector uses deep learning to classify spike signals from artifacts [24], and Melinda et al proposed a supervised deep learning model that uses Convolution neural network and long short-term memory to classify the different action potentials on microelectrode array (MEA) recordings [25]. In this paper, we propose an efficient unsupervised deep learning spike sorting model where manual labeling is not required and show that it can address the problems and the limitations of previous template matching methods.…”