Deep Learning is a very active and important area for building Computer-Aided Diagnosis (CAD) applications. This work aims to present a hybrid model to classify lung ultrasound (LUS) videos captured by convex transducers to diagnose COVID-19. A Convolutional Neural Network (CNN) performed the extraction of spatial features, and the temporal dependence was learned using a Long Short-Term Memory (LSTM). Different types of convolutional architectures were used for feature extraction. The hybrid model (CNN-LSTM) hyperparameters were optimized using the Optuna framework. The best hybrid model was composed of an Xception pre-trained on ImageNet and an LSTM containing 512 units, configured with a dropout rate of 0.4, two fully connected layers containing 1024 neurons each, and a sequence of 20 frames in the input layer (20×2018). The model presented an average accuracy of 93% and sensitivity of 97% for COVID-19, outperforming models based purely on spatial approaches. Furthermore, feature extraction using transfer learning with models pre-trained on ImageNet provided comparable results to models pre-trained on LUS images. The results corroborate with other studies showing that this model for LUS classification can be an important tool in the fight against COVID-19 and other lung diseases.
Convolutional Neural Networks (CNNs) have been successfully applied in the medical diagnosis of different types of diseases. However, selecting the architecture and the best set of hyperparameters among the possible combinations can be a significant challenge. The purpose of this work is to investigate the use of the Hyperband optimization algorithm in the process of optimizing a CNN applied to the diagnosis of SARS-Cov2 disease (COVID-19). The test was performed with the Optuna framework, and the optimization process aimed to optimize four hyperparameters: (1) backbone architecture, (2) the number of inception modules, (3) the number of neurons in the fully connected layers, and (4) the learning rate. CNNs were trained on 2175 computed tomography (CT) images. The CNN that was proposed by the optimization process was a VGG16 with five inception modules, 128 neurons in the two fully connected layers, and a learning rate of 0.0027. The proposed method achieved a sensitivity, precision, and accuracy of 97%, 82%, and 88%, outperforming the sensitivity of the Real-Time Polymerase Chain Reaction (RT-PCR) tests (53–88%) and the accuracy of the diagnosis performed by human experts (72%).
O objetivo dessa pesquisa foi analisar a produção de artigos no campo da política pública em lazer no Brasil nas dimensões do direito e do reconhecimento social. Para tanto, foram selecionados 40 artigos coletados junto às bases de dados Lilacs, Scielo e Portal de Periódicos CAPES. Averiguou-se que esse campo de investigação tem sido intensificado com o aumento exponencial das publicações, a partir de 2005, e que a Constituição de 1988 impactou as pesquisas em lazer, bem como as ações ligadas ao governo, especialmente com a criação do Ministério do Esporte. A análise dos artigos evidenciou a existência de lacunas na produção de conhecimento, notadamente em relação ao entendimento de políticas públicas de lazer como direito e reconhecimento social, bem como a maneira esparsa dessa produção, uma vez a dificuldade de se estabelecer diálogo entre os campos acadêmico, político burocrático e societal.
Este texto é uma análise do voleibol feminino de alto rendimento a partir de quatro parâmetros específicos: o tempo de rally, o erro de saque, a estatura e o desempenho das jogadoras. Este estudo é de caráter transversal, quantitativo, descritivo e faz uso de banco de dados já disponível. As possibilidades de prever bons resultados são a força motivadora de estudos voltados para o desempenho nos esportes. Dentre as conclusões, a análise sugere que as jogadoras de voleibol de alto rendimento estão sujeitas a fortes pressões por bons resultados. Tanto os desempenhos espetaculares quanto os desempenhos fracos, abaixo do esperado, são em grande medida fruto dessas pressões a que a jogadora está submetida e em muitos casos impõe os limites da própria carreira da jogadora.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.