To study the electrophysiological properties of neuronal networks, in vitro studies based on microelectrode arrays have become a viable tool for analysis. Although in constant progress, a challenging task still remains in this area: the development of an efficient spike sorting algorithm that allows an accurate signal analysis at the single-cell level. Most sorting algorithms currently available only extract a specific feature type, such as the principal components or Wavelet coefficients of the measured spike signals in order to separate different spike shapes generated by different neurons. However, due to the great variety in the obtained spike shapes, the derivation of an optimal feature set is still a very complex issue that current algorithms struggle with. To address this problem, we propose a novel algorithm that (i) extracts a variety of geometric, Wavelet and principal component-based features and (ii) automatically derives a feature subset, most suitable for sorting an individual set of spike signals. Thus, there is a new approach that evaluates the probability distribution of the obtained spike features and consequently determines the candidates most suitable for the actual spike sorting. These candidates can be formed into an individually adjusted set of spike features, allowing a separation of the various shapes present in the obtained neuronal signal by a subsequent expectation maximisation clustering algorithm. Test results with simulated data files and data obtained from chick embryonic neurons cultured on microelectrode arrays showed an excellent classification result, indicating the superior performance of the described algorithm approach.

Multi-unit recording from neuronal networks cultured on microelectrode arrays (MEAs) is a widely used approach to achieve basic understanding of network properties, as well as the realization of cell-based biosensors. However, network formation is random under primary culture conditions, and the cellular arrangement often performs an insufficient fit to the electrode positions. This results in the successful recording of only a small fraction of cells. One possible approach to overcome this limitation is to raise the number of cells on the MEA, thereby accepting an increased complexity of the network. In this study, we followed an alternative strategy to increase the portion of neurons located at the electrodes by designing a network in confined geometries. Guided settlement and outgrowth of neurons is accomplished by taking control over the adhesive properties of the MEA surface. Using microcontact printing a triangular twodimensional pattern of the adhesion promoter poly-Dlysine was applied to the MEA offering a meshwork that at the same time provides adhesion points for cell bodies matching the electrode positions and gives frequent branching points for dendrites and axons. Low density neocortical networks cultivated under this condition displayed similar properties to random networks with respect to the cellular morphology but had a threefold higher electrode coverage. Electrical activity was dominated by periodic burst firing that could pharmacologically be modulated. Geometry of the network and electrical properties of the patterned cultures were reproducible and displayed long-term stability making the combination of surface structuring and multi-site recording a promising tool for biosensor applications.

Mental disorders are among the leading causes of disability worldwide. The first step in treating these conditions is to obtain an accurate diagnosis. Machine learning algorithms can provide a possible solution to this problem, as we describe in this work. We present a method for the automatic diagnosis of mental disorders based on the matrix of connections obtained from EEG time series and deep learning. We show that our approach can classify patients with Alzheimer’s disease and schizophrenia with a high level of accuracy. The comparison with the traditional cases, that use raw EEG time series, shows that our method provides the highest precision. Therefore, the application of deep neural networks on data from brain connections is a very promising method for the diagnosis of neurological disorders.

No abstract