No abstract

Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

Three intelligent information access systems were successfully used to evaluate the teacher's perceptions regarding the utility of these systems in learning activities. The results of this study showed that integration of reliable sources of information, bilingualism and selective annotation of concepts were the most valued features by the teachers, who also considered the incorporation of these systems into learning activities to be potentially very useful. In addition, in the context of our experimental conditions, our work provides useful insights into the way to appropriately integrate this type of intelligent information access systems into learning activities, revealing key themes to consider when developing such approaches.

A high proportion of children with Attention problems (ADHD) experience motor competence problems. The present study sought to compare the motor competence between a group of ADHD students and a normative sample before and after controlling for motor coordination problems, and check if there are differences between the group with ADHD and the group with DT, depending on the presence or not of the DCD concurrent with the ADHD.  A total of 22 children with ADHD combined type (ADHD-CT; 12–13 years, SD 0.7, 16 males, 6 females) and 23 age-matched typically developing children with no movement difficulties (12-13 years, SD 0.7 16 males, 7 females) participated in this study. Motor coordination was measured using the Movement Assessment Battery for Children-2nd Edition (MABC-2). ADHD symptoms were assessed by the school’s Department of Psychology.The ADHD diagnosis is based on  diagnostic criteria established by the Diagnostic and statistical manual of mental disorders, fifth edition (DSM-5), and the application of the following behavioral scales and evaluation of executive functions have been followed: Child Behavior Checklist for ages; Behavior Ratting Inventory of Executive Functions (BRIEF); Scales for the Evaluation of ADHD (EDAH). Based on the MABC-2 score (percentile score ≤ 5th), ADHD children were classified into two groups: co-occurring DCD/ADHD and ADHD group. Results showed that children with ADHD and typically developing (TD) children showed big individual differences on all motor skill areas and on overall percentile scores. Thirteen children with ADHD were delayed, and three were at risk for motor delays. Only four TD children were at risk for motor delays. DCD/ADHD group scored significantly lower than the TD group across all motor skill areas, while ADHD group scored lower than the TD group only on manual dexterity.