In this paper, we present a fully automatic brain tumor segmentation and classification model using a Deep Convolutional Neural Network that includes a multiscale approach. One of the differences of our proposal with respect to previous works is that input images are processed in three spatial scales along different processing pathways. This mechanism is inspired in the inherent operation of the Human Visual System. The proposed neural model can analyze MRI images containing three types of tumors: meningioma, glioma, and pituitary tumor, over sagittal, coronal, and axial views and does not need preprocessing of input images to remove skull or vertebral column parts in advance. The performance of our method on a publicly available MRI image dataset of 3064 slices from 233 patients is compared with previously classical machine learning and deep learning published methods. In the comparison, our method remarkably obtained a tumor classification accuracy of 0.973, higher than the other approaches using the same database.

Information theory allows us to investigate information processing in neural systems in terms of information transfer, storage and modification. Especially the measure of information transfer, transfer entropy, has seen a dramatic surge of interest in neuroscience. Estimating transfer entropy from two processes requires the observation of multiple realizations of these processes to estimate associated probability density functions. To obtain these necessary observations, available estimators typically assume stationarity of processes to allow pooling of observations over time. This assumption however, is a major obstacle to the application of these estimators in neuroscience as observed processes are often non-stationary. As a solution, Gomez-Herrero and colleagues theoretically showed that the stationarity assumption may be avoided by estimating transfer entropy from an ensemble of realizations. Such an ensemble of realizations is often readily available in neuroscience experiments in the form of experimental trials. Thus, in this work we combine the ensemble method with a recently proposed transfer entropy estimator to make transfer entropy estimation applicable to non-stationary time series. We present an efficient implementation of the approach that is suitable for the increased computational demand of the ensemble method's practical application. In particular, we use a massively parallel implementation for a graphics processing unit to handle the computationally most heavy aspects of the ensemble method for transfer entropy estimation. We test the performance and robustness of our implementation on data from numerical simulations of stochastic processes. We also demonstrate the applicability of the ensemble method to magnetoencephalographic data. While we mainly evaluate the proposed method for neuroscience data, we expect it to be applicable in a variety of fields that are concerned with the analysis of information transfer in complex biological, social, and artificial systems.

This paper introduces the development of a customized virtual reality system based on a serious game which allows the user to carry out physical and cognitive rehabilitation therapies using a natural user interface based on Microsoft© Kinect. Within these serious games you can find the exergames. It is a type of serious game which aims to stimulate body mobility through an immersive experience that situates the user inside virtual interactive landscapes. This type of game has become popular in recent years thanks to the creation of consoles like Nintendo Wii, Playstation or Xbox, which use gestural interaction game interfaces. Likewise, these technologies have become extremely useful tools in rehabilitation, and they are expected to permit a reduction of costs in socio-sanitary environments. The proposed virtual reality platform consists of different types of exercises by which the user is able to train or rehabilitate several aspects such as strength, aerobic or cognitive capacities. The system has been modelled so that the physical presence of a therapist is not required during the course of the session and there is no need to wear any kind of marker or sensor. Moreover, all parameters of the different exercises can be configured without the physical presence of a therapist. The reports of each session can also be read offline, therefore, the therapist will always know if a user has performed the session in a good way and act accordingly modifying whatever he deems necessary in the patient's therapy. Due to these facts the system developed and presented in this article is a rehabilitation system based on remote assistance. It is important that this type of serious games accomplish all the functionalities a videogame fulfils at the same time that accomplish specific functionalities in its therapeutic environment. Remarkably, it is required an adaptation to the patient's abilities to avoid frustration and provide immediate feedback to the user during the exercises. In our system, the users are monitored and receive an audio-visual feedback during the session, so that they know in real-time if they are correctly doing the exercises of the specific therapy that was designed for them