COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformer
This work addresses the problem of efficient and accurate COVID-19 diagnosis for medical applications, but it appears incremental as it applies existing transformer-based methods to a specific dataset.
The authors tackled COVID-19 detection in chest X-ray images by combining Swin Transformer and Transformer in Transformer, achieving an accuracy of 0.9475 on a test set for classifying COVID-19, Pneumonia, and Normal cases.
The Coronavirus Disease 2019 (COVID-19) has spread globally and caused serious damage. Chest X-ray images are widely used for COVID-19 diagnosis and the Artificial Intelligence method can increase efficiency and accuracy. In the Challenge of Chest XR COVID-19 detection in Ethics and Explainability for Responsible Data Science (EE-RDS) conference 2021, we proposed a method that combined Swin Transformer and Transformer in Transformer to classify chest X-ray images as three classes: COVID-19, Pneumonia, and Normal (healthy) and achieved 0.9475 accuracies on the test set.