SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network

作者：

Highlights：

• Introduction of a new architecture SARS-Net.

• It is a CADx system combining graph convolutional network and convolutional neural network model for detecting abnormalities in a patient's CXR images for the presence of COVID-19 infection in a patient.

• We introduce and evaluate the performance of a custom-made deep learning architecture SARS-Net, to classify and detect the Chest X-ray images for COVID-19 diagnosis.

• Quantitative analysis shows that the proposed model achieves more accuracy than the previously mentioned state-of-the-art methods.

• It was found that the model achieved an accuracy of 97.60% and a sensitivity of 92.90% on the validation set.

摘要

•Introduction of a new architecture SARS-Net.•It is a CADx system combining graph convolutional network and convolutional neural network model for detecting abnormalities in a patient's CXR images for the presence of COVID-19 infection in a patient.•We introduce and evaluate the performance of a custom-made deep learning architecture SARS-Net, to classify and detect the Chest X-ray images for COVID-19 diagnosis.•Quantitative analysis shows that the proposed model achieves more accuracy than the previously mentioned state-of-the-art methods.•It was found that the model achieved an accuracy of 97.60% and a sensitivity of 92.90% on the validation set.

论文关键词：Convolutional neural network,Graph convolutional network,COVID-19 detection,Chest X-ray,Deep learning

论文评审过程：Received 10 April 2021, Revised 5 August 2021, Accepted 12 August 2021, Available online 25 August 2021, Version of Record 31 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108255