Tool to Assist in the Prognosis of covid-19 and Pneumonia in Robust or Restricted Computational Environments
Resumo
A triagem eficaz de pacientes infectados pelo covid-19 desempenha um papel crucial no combate a essa doença, sendo uma das principais abordagem o exame de radiografia do tórax, no entanto seu diagnóstico pode ser confundido com de uma pneumonia. Neste estudo desenvolvemos quatro modelos utilizando Convolutional Neural Network (CNN) treinadas com 30.000 imagens, capazes de classificar uma imagem de raio-x de pulmão em normal, com pneumonia ou com covid-19, com uma acurácia próxima de 90%. Além disso, fazemos uma análise de custo benefício dos modelos considerando a implementação em sistemas mais restritos, como em sistemas embarcados e sistemas com maior poder de processamento, como sistemas em servidores.
Palavras-chave:
Covid-19, Pneumonia, Redes neurais convolucionais, Radiografia, Acurácia
Referências
Arduino (2023) “Especificação do produto nRF52840 v.1.1”, [link], Junho.
Chen N, Zhou M, Dong X, et al (2020). Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. Lancet 2020;395:507-13. 10.1016/S0140-6736(20)30211-7.
Guan WJ, Ni ZY, Liang WH, et al (2020). Clinical Characteristics of Coronavirus Disease 2019 in China. N Engl J Med 2020;382:1708-20. 10.1056/NEJMoa2002032
Hernandez, D., Pereira, R. and Georgevia, P. (2020). COVID-19 detection through X-Ray chest images. International Conference Automatics and Informatics (ICAI).
Hossein, Wong, A., Gunraj, H., et al. (2022). “COVIDx CXR-3”, [link]. Fevereiro.
Kermany, D., Zhang, K. and Goldbaum, M. (2018). Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification. v. 2.
Mohammadi, R., SalehiM., Ghaffari, H., et al. (2020). Transfer Learning-Based Automatic Detection of Coronavirus Disease 2019 (COVID-19) from Chest X-ray Images. Journal of Biomedical Physics and Engineering, p.559-568.
ONEIROS (2015). “Keras API Reference – Applications”. 2015. [link]
Organização Mundial da Saúde (2023) “COVID-19 Weekly Epidemiological Update”, [link], Junho.
Ozturk, T., Talo, M.,Yildirim, E., Baloglu U.,Yildirim. et al. (2020) Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, v. 121.
Radiological Society of North America (2018) “RSNA Pneumonia Detection Challenge”, [link]. Agosto.
Tangudu, V., Kakarla, J. and Venkateswarlu, I. (2022) “COVID-19 detection from chest x-ray using MobileNet and residual separable convolution block”, Soft Computer, p. 2197-2208
Wang, L., Lin, Z. and Wong, A., (2020) “COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images”, Sci Rep. v. 10.
Yang, D., Martinez, C., Visuña, L. et al. (2021) “Detection and analysis of COVID-19 in medical images using deep learning techniques”, Sci Rep. v. 11.
Chen N, Zhou M, Dong X, et al (2020). Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. Lancet 2020;395:507-13. 10.1016/S0140-6736(20)30211-7.
Guan WJ, Ni ZY, Liang WH, et al (2020). Clinical Characteristics of Coronavirus Disease 2019 in China. N Engl J Med 2020;382:1708-20. 10.1056/NEJMoa2002032
Hernandez, D., Pereira, R. and Georgevia, P. (2020). COVID-19 detection through X-Ray chest images. International Conference Automatics and Informatics (ICAI).
Hossein, Wong, A., Gunraj, H., et al. (2022). “COVIDx CXR-3”, [link]. Fevereiro.
Kermany, D., Zhang, K. and Goldbaum, M. (2018). Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification. v. 2.
Mohammadi, R., SalehiM., Ghaffari, H., et al. (2020). Transfer Learning-Based Automatic Detection of Coronavirus Disease 2019 (COVID-19) from Chest X-ray Images. Journal of Biomedical Physics and Engineering, p.559-568.
ONEIROS (2015). “Keras API Reference – Applications”. 2015. [link]
Organização Mundial da Saúde (2023) “COVID-19 Weekly Epidemiological Update”, [link], Junho.
Ozturk, T., Talo, M.,Yildirim, E., Baloglu U.,Yildirim. et al. (2020) Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, v. 121.
Radiological Society of North America (2018) “RSNA Pneumonia Detection Challenge”, [link]. Agosto.
Tangudu, V., Kakarla, J. and Venkateswarlu, I. (2022) “COVID-19 detection from chest x-ray using MobileNet and residual separable convolution block”, Soft Computer, p. 2197-2208
Wang, L., Lin, Z. and Wong, A., (2020) “COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images”, Sci Rep. v. 10.
Yang, D., Martinez, C., Visuña, L. et al. (2021) “Detection and analysis of COVID-19 in medical images using deep learning techniques”, Sci Rep. v. 11.
Publicado
25/09/2023
Como Citar
SILVA, João Felipe Barros da; FERNANDES, Sílvio Roberto.
Tool to Assist in the Prognosis of covid-19 and Pneumonia in Robust or Restricted Computational Environments. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 20. , 2023, Belo Horizonte/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 854-865.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2023.234495.
