ChestX-Ray6: Prediction of multiple diseases including COVID-19 from chest X-ray images using convolutional neural network

作者：

Highlights：

• Achieved an accuracy of 97.60% and a recall of 98%.

• Merged several database to create multi-disease which includes 6 classes of disease.

• Trained ChestX-ray6 model on 21000 chest x-ray images of 6 classes.

• Balanced the training data using augmentation.

• Used our pre-trained ChestX-ray6 of 6 classes model for binary classification.

摘要

•Achieved an accuracy of 97.60% and a recall of 98%.•Merged several database to create multi-disease which includes 6 classes of disease.•Trained ChestX-ray6 model on 21000 chest x-ray images of 6 classes.•Balanced the training data using augmentation.•Used our pre-trained ChestX-ray6 of 6 classes model for binary classification.

论文关键词：Convolutional neural network (CNN),ChestX-Ray6,COVID19,Cardiomegaly,DenseNet121,Lung opacity,MobileNetV2,VGG19,Pneumonia,Pleural,ResNet50

论文评审过程：Received 18 February 2021, Revised 10 August 2022, Accepted 13 August 2022, Available online 27 August 2022, Version of Record 1 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118576