Sistema Regional de Información
en línea para Revistas Científicas de América Latina,
el Caribe, España y Portugal

Is it possible to have an interdisciplinarity between Communication and Health courses in the teaching of Community Communication? Theoretically, some authors, especially in the field of health, already discuss this integration (Araújo & Cardoso, 2007). But beyond a bibliographical production, this integration is almost non-existent in Brazilian classrooms. Thus, the objective of the article is to share an interdisciplinary experience in the teaching of Community Communication, with emphasis on citizenship practices, involving the Communication and Medicine courses of a public university located in Northeast Brazil. We are aligned with Peruzzo (2013, p. 176) in the understanding that the Community Communication “contributes to the formation of citizens capable of understanding the world and organizing itself to transform it”.

DOI: 10.26439/contratexto2020.n033.4790 The proposal is to open the discussion, from oral epistemology, as the basis for other epistemologies, to think about communication to imagine desirable futures for Latin America. The idea of feeling as a decentralization of the perspectives that make it possible to understand open educational processes in the uncertainty of the answers. Do not follow models, molds or manuals, but the power of the imagination as a resistance strategy against the dogmas that are installed as ways of thinking. It is the interlocutions that potentiate new questions that should not necessarily be answered. They serve to question better. We cannot understand the action of imagining but we understand the episteme of the interlocutions that pass us through time, to imagine is to be in miscellaneous. Today, especially, imagining is one of the forms of resistance.

The gender gap between man and women participation in Science, Technology, Engineering and Mathematics (STEM) is regrettably universal, and generally unacceptably broad. In addition, this gap is particularly noticeable in the Electrical Engineering and Computer Engineering (EECS) careers. Several international organizations and universities in North America, Europe and Latin America have designed programs to address this important problem, showing varying degrees of success. In many of these programs the idea is to work with high school girls, seeking to bring them key knowledge of the disciplines of STEM and encourage them to choose careers in the area. Among other activities, these programs offer presentations, talks, or short courses in a given period at the university itself, taught by women teachers in the area applying the role model approach. This article presents the experience of the Facultad de Ingenier ??a (School of Engineering) of the Universidad de la Rep ?ublica, Uruguay, on the occasion of the Girls in Information and Communication Technologies (ICT) day. In particular, workshops for robotics, circuits and maps making were held for high school girls as a way to promote ICT careers in Uruguay.

A neural network is a mathematical model that is able to perform a task automatically or semi-automatically after learning the human knowledge that we provided. Moreover, a Convolutional Neural Network (CNN) is a type of neural network that has shown to efficiently learn tasks related to the area of image analysis, such as image segmentation, whose main purpose is to find regions or separable objects within an image. A more specific type of segmentation, called semantic segmentation, guarantees that each region has a semantic meaning by giving it a label or class. Since CNNs can automate the task of image semantic segmentation, they have been very useful for the medical area, applying them to the segmentation of organs or abnormalities (tumors). This work aims to improve the task of binary semantic segmentation of volumetric medical images acquired by Magnetic Resonance Imaging (MRI) using a pre-existing Three-Dimensional Convolutional Neural Network (3D CNN) architecture. We propose a formulation of a loss function for training this 3D CNN, for improving pixel-wise segmentation results. This loss function is formulated based on the idea of adapting a similarity coefficient, used for measuring the spatial overlap between the prediction and ground truth, and then using it to train the network. As contribution, the developed approach achieved good performance in a context where the pixel classes are imbalanced. We show how the choice of the loss function for training can affect the nal quality of the segmentation. We validate our proposal over two medical image semantic segmentation datasets and show comparisons in performance between the proposed loss function and other pre-existing loss functions used for binary semantic segmentation.