Evaluation of Convolutional Neural Networks for COVID-19 Classification on Chest X-Rays

  • Felipe André Zeiser UNISINOS
  • Cristiano André da Costa UNISINOS
  • Gabriel de Oliveira Ramos UNISINOS
  • Henrique Bohn UNISINOS
  • Ismael Santos UNISINOS
  • Rodrigo da Rosa Righi UNISINOS

Resumo


Early identification of patients with COVID-19 is essential to enable adequate treatment and to reduce the burden on the health system. The gold standard for COVID-19 detection is the use of RT-PCR tests. However, due to the high demand for tests, these can take days or even weeks in some regions of Brazil. Thus, an alternative for detecting COVID-19 is the analysis of Digital Chest X-rays (XR). Changes due to COVID-19 can be detected in XR, even in asymptomatic patients. In this context, models based on deep learning have great potential to be used as support systems for diagnosis or as screening tools. In this paper, we propose the evaluation of convolutional neural networks to identify pneumonia due to COVID-19 in XR. The proposed methodology consists of a preprocessing step of the XR, data augmentation, and classification by the convolutional architectures DenseNet121, InceptionResNetV2, InceptionV3, MovileNetV2, ResNet50, and VGG16 pre-trained with the ImageNet dataset. The obtained results for our methodology demonstrate that the VGG16 architecture presented a superior performance in the classification of XR, with an Accuracy of 85.11%, Sensitivity of 85.25%, Specificity of 85.16%, F1-score of 85.03%, and an AUC of 0.9758.

Palavras-chave: COVID-19, Chest X-Rays, Deep learning, Convolutional neural network
Publicado
29/11/2021
Como Citar

Selecione um Formato
ZEISER, Felipe André; COSTA, Cristiano André da; RAMOS, Gabriel de Oliveira; BOHN, Henrique; SANTOS, Ismael; RIGHI, Rodrigo da Rosa. Evaluation of Convolutional Neural Networks for COVID-19 Classification on Chest X-Rays. In: BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 10. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . ISSN 2643-6264.