DACov: a deeper analysis of data augmentation on the computed tomography segmentation problem

Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we present a deeper analysis of how data augmentation techniques improve segmentation performance on this problem. We evaluate (Formula presented.) traditional augmentation techniques on five public datasets. Six different probabilities of applying each augmentation technique on an image were evaluated. We also assess a different training methodology where the training subsets are combined into a single larger set. All networks were evaluated through a (Formula presented.) -fold cross-validation strategy, resulting in over (Formula presented.) experiments. We also propose a novel data augmentation technique based on Generative Adversarial Networks (GANs) to create new healthy and unhealthy lung CT images, evaluating four variations of our approach with the same six probabilities of the traditional methods. Our findings show that GAN-based techniques and spatial-level transformations are the most promising for improving the learning of deep models on this problem, with the StarGAN v2 + F with a probability of (Formula presented.) achieving the highest F-score value on the Ricord1a dataset in the unified training strategy. Our code is publicly available at https://github.com/VRI-UFPR/DACov2022.Copyright © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Spark in the Dark: Evaluating Encoder-Decoder Pairs for COVID-19 CT's Semantic Segmentation

With the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained a lot of attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) turned highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of Covid-19 and was widely explored since the Covid-19 outbreak. In the robotic field, Semantic Segmentation of organs and CTs are widely used in robots developed for surgery tasks. As new methods and new datasets are proposed quickly, it becomes apparent the necessity of providing an extensive evaluation of those methods. To provide a standardized comparison of different architectures across multiple recently proposed datasets, we propose in this paper an extensive benchmark of multiple encoders and decoders with a total of 120 architectures evaluated in five datasets, with each dataset being validated through a five-fold cross-validation strategy, totaling 3.000 experiments. To the best of our knowledge, this is the largest evaluation in number of encoders, decoders, and datasets proposed in the field of Covid-19 CT segmentation. © 2021 IEEE.

MODEL OF ACADEMIC MANAGEMENT OF HYBRID ENVIRONMENTS FOR PROFESSIONAL TRAINING AT UNIVERSIDAD UNIANDES, QUEVEDO EXTENSION

UNIANDES Quevedo University, as well as the higher education system, has been affected by the impact of COVID 19. This paper focuses on this problem by studying how the university has responded in the educational field to the teaching challenges involved in abruptly migrating to virtuality. The answer is the academic management model for migration to virtuality, which has allowed empowering teachers in the solution of the complex didactic and communicative problems that occur in technological training environments. Theoretical, empirical and mathematical statistical methods have been used for the research. The result has been supported by the teaching indicators achieved in the last two academic periods taught at the university.

ACADEMIC STRATEGY TO DEVELOP VIRTUAL SCENARIOS FOR PROFESSIONAL TRAINING IN THE CONTEXT OF THE COVID-19 PANDEMIC

The development of strategies to face the transition from the face-to-face modality to the virtual and/or hybrid modality at the pedagogical and didactic level at the university, in the face of the emergency created by the Covid-19 pandemic, has conditioned the question: How to ensure from the academic environment the professional training processes at UNIANDES Quevedo? It is developed as an action-participatory research and various methods and techniques are used, among which are: the analytical-synthetic method, historical-logical, modeling and the systemic method. The results of the investigative process are realized, once the general objective is achieved, by developing a strategy for the management of educational change in the university organization that allows to assume the hybrid virtual modality in the teaching and learning processes of the UNIANDES-Quevedo headquarters.