Transfer learning approach to Classify the X-ray image that corresponds to corona disease Using ResNet50 pretrained by ChexNet
Mahyar Bolhassani
TL;DR
This study tackles the challenge of rapidly diagnosing COVID-19 from chest X-rays amidst similarities to other respiratory diseases. It explores transfer learning with a ResNet50 backbone pretrained on ImageNet and, separately, a DenseNet121 pretrained on CheXNet, evaluating binary and multi-class classification on the CoronaHack dataset while addressing severe class imbalance with weighted sampling and focal loss. DenseNet121 pretrained on CheXNet consistently yields the strongest performance, and focal loss improves generalization on imbalanced data, especially after augmenting the dataset with extra COVID-19 samples. The work highlights the impact of domain-specific pretraining and imbalance-aware losses on diagnostic accuracy, while acknowledging that limited COVID-19 data constrains peak performance and suggesting semi-supervised or data-expansion approaches for future gains.
Abstract
Coronavirus adversely has affected people worldwide. There are common symptoms between the Covid19 virus disease and other respiratory diseases like pneumonia or Influenza. Therefore, diagnosing it fast is crucial not only to save patients but also to prevent it from spreading. One of the most reliant methods of diagnosis is through X-ray images of a lung. With the help of deep learning approaches, we can teach the deep model to learn the condition of an affected lung. Therefore, it can classify the new sample as if it is a Covid19 infected patient or not. In this project, we train a deep model based on ResNet50 pretrained by ImageNet dataset and CheXNet dataset. Based on the imbalanced CoronaHack Chest X-Ray dataset introducing by Kaggle we applied both binary and multi-class classification. Also, we compare the results when using Focal loss and Cross entropy loss.