At the end of 2019, the World Health Organization (WHO) reported pneumonia that started in Wuhan, China, as a global emergency problem. Researchers quickly advanced in research to try to understand this COVID-19 and sough solutions for the front-line professionals fighting this fatal disease. One of the tools to aid in the detection, diagnosis, treatment, and prevention of this disease is computed tomography (CT). CT images provide valuable information on how this new disease affects the lungs of patients. However, the analysis of these images is not trivial, especially when researchers are searching for quick solutions. Detecting and evaluating this disease can be tiring, time-consuming, and susceptible to errors. Thus, in this study, we aim to automatically segment infections caused by COVID19 and provide quantitative measures of these infections to specialists, thus serving as a support tool. We use a database of real clinical cases from Pedro Ernesto University Hospital of the State of Rio de Janeiro, Brazil. The method involves five steps: lung segmentation, segmentation and extraction of pulmonary vessels, infection segmentation, infection classification, and infection quantification. For the lung segmentation and infection segmentation tasks, we propose modifications to the traditional U-Net, including batch normalization, leaky ReLU, dropout, and residual block techniques, and name it as Residual U-Net. The proposed method yields an average Dice value of 77.1% and an average specificity of 99.76%. For quantification of infectious findings, the proposed method achieves results like that of specialists, and no measure presented a value of ρ < 0.05 in the paired t-test. The results demonstrate the potential of the proposed method as a tool to help medical professionals combat COVID-19. fight the COVID-19.
RESUMOO glaucoma é uma doença silenciosa que pode levar a cegueira caso não seja tratada com urgência. Métodos de diagnóstico que utilizam inteligên-cia computacional têm sido propostos com a finalidade de aumentar a taxa de detecções da doença ainda na sua fase inicial, e proporcionar melhor qualidade de vida aos pacientes. Porém, a descoberta de melhores técnicas e métodos de diagnóstico Palavras-chave: Diagnóstico Assistido por Computadores, Meta Aprendiza-gem, Otimização Bayesiana, Diagnóstico de Glaucoma, Extração de Carac-terísticas.
Glaucoma is an asymptomatic disease that can bring people to blindness if not early detected. Computational intelligence methods have been proposed to provide a computerized diagnosis that can guide patients to the appropriate treatment. However, these techniques face methodology optmization problems, which depends on the choices of many algorithms from diferent knowledge areas. This paper suggests a solution through meta-learning of preprocessing methods, decomposition and features extraction which have to be used efficiently in order to solve the problem. Current results are promissing, reaching 91.24% accuracy after 50 evaluations and it is suposed to improve proportionally to the number of evaluations.
RESUMOO glaucoma é uma doença ocular caracterizada por neuropatia óptica e distúrbio visual que corresponde á escavação no disco óptico e á degeneração das fibras nervosas ópticas. Geralmente é causado pelo aumento na pressão intra-ocular, que danifica o nervo óptico, resultando em perda gra-dual da visão. Um tratamento eficaz é a redução e controle da pressão intra-ocular (PIO) que deve acontecer o mais precocemente possível de modo a limitar a progressão da doença. Vários trabalhos tem sido propostos para a realização do diagnóstico automático de glaucoma. Assim, é vital o desenvolvimento de uma ferramenta
O Teste de Brückner é um exame oftalmológico que visa detectar patologias oculares precocemente. Ele opera através da identificação de um reflexo vermelho na região ocular após a incidência de um feixe luminoso. Este trabalho apresenta um novo método para identificação automática de um possível problema ocular em imagens de reflexo vermelho oriundas do Teste de Brückner através de descritores de cor. Utilizando uma otimização na escolha dos métodos de pré processamento em conjunto com os descritores de cor dominante e os momentos de cor, o método proposto alcançou 92% de acurácia, 98% de especificidade e 76% de sensibilidade utilizando o classificador XGBoost.
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.