Neural Networks to Recognize Patterns in Topographic Images of Cortical Electrical Activity of Patients with Neurological Diseases.

Software such as EEGLab has enabled the treatment and visualization of the tracing and cortical topography of the electroencephalography (EEG) signals. In particular, the topography of the cortical electrical activity is represented by colors, which make it possible to identify functional differences between cortical areas and to associate them with various diseases. The use of cortical topography with EEG origin in the investigation of diseases is often not used due to the representation of colors making it difficult to classify the disease. Thus, the analyses have been carried out, mainly, based on the EEG tracings. Therefore, a computer system that recognizes disease patterns through cortical topography can be a solution to the diagnostic aid. In view of this, this study compared five models of Convolutional Neural Networks (CNNs), namely: Inception v3, SqueezeNet, LeNet, VGG-16 and VGG-19, in order to know the patterns in cortical topography images obtained with EEG, in Parkinson's disease, Depression and Bipolar Disorder. SqueezeNet performed better in the 3 diseases analyzed, with Parkinson's disease being better evaluated for Accuracy (88.89%), Precison (86.36%), Recall (91.94%) and F1 Score (89.06%), the other CNNs had less performance. In the analysis of the values of the Area under ROC Curve (AUC), SqueezeNet reached (93.90%) for Parkinson's disease, (75.70%) for Depression and (72.10%) for Bipolar Disorder. We understand that there is the possibility of classifying neurological diseases from cortical topographies with the use of CNNs and, thus, creating a computational basis for the implementation of software for screening and possible diagnostic assistance.

Percolation theory for the recognition of patterns in topographic images of the cortical activity.

Electroencephalogram (EEG) is one of the mechanisms used to collect complex data. Its use includes evaluating neurological disorders, investigating brain function and correlations between EEG signals and real or imagined movements. The Topographic Image of Cortical Activity (TICA) records obtained by the EEG make it possible to observe, through color discrimination, the cortical areas that represent greater or lesser activity. Percolation Theory (PT) reveals properties on the aspects of fluid spreading from a central point, these properties being related to the aspects of the medium, topological characteristics and ease of penetration of a fluid in materials. The hypothesis presented so far considers that synaptic activities originate in points and spread from them, causing different areas of the brain to interact in a diffusive associative behavior, generating electric and magnetic fields by the currents that spread through the brain tissue and have an effect on the scalp sensors. Brain areas spatially separated create large-scale dynamic networks that are described by functional and effective connectivity. The proposition is that this phenomenon behaves like a fluidic spreading, so we can use the PT, through the topological analysis we detect specific signatures related to neural phenomena that manifest changes in the behavior of synaptic diffusion. This signature must be characterized by the Fractal Dimension (FD) values of the scattering clusters, these values will be used as properties in the k-Nearest Neighbors (kNN) method, an TICA will be categorized according to the degree of similarity to the preexisting patterns. In this context, our hypothesis will consolidate as a more computational resource in the service of medicine and another way that opens with the possibility of analysis and detailed inferences of the brain through TICA that go beyond a simply visual observation, as it happens in the present day.