COVID-Transformer: Interpretable COVID-19 Detection Using Vision Transformer for Healthcare

TLDR

Accurate, rapid COVID‑19 testing is critical, yet testing capacity is limited and manual chest X‑ray review is slow and error‑prone. The study proposes a Vision Transformer‑based deep learning pipeline to detect COVID‑19 from chest X‑ray images. The authors assembled a 30 k‑image chest X‑ray dataset from three open‑source sources, fine‑tuned several baseline CNNs, and trained a Vision Transformer to classify COVID‑19. The Vision Transformer achieved 98 % accuracy (AUC 99 %) on binary detection, 92 % accuracy (AUC 98 %) on multi‑class classification, outperformed all baseline CNNs, and its Grad‑CAM visualizations aid radiologist interpretation.

Abstract

In the recent pandemic, accurate and rapid testing of patients remained a critical task in the diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of the sudden increase in cases, most countries have faced scarcity and a low rate of testing. Chest X-rays have been shown in the literature to be a potential source of testing for COVID-19 patients, but manually checking X-ray reports is time-consuming and error-prone. Considering these limitations and the advancements in data science, we proposed a Vision Transformer-based deep learning pipeline for COVID-19 detection from chest X-ray-based imaging. Due to the lack of large data sets, we collected data from three open-source data sets of chest X-ray images and aggregated them to form a 30 K image data set, which is the largest publicly available collection of chest X-ray images in this domain to our knowledge. Our proposed transformer model effectively differentiates COVID-19 from normal chest X-rays with an accuracy of 98% along with an AUC score of 99% in the binary classification task. It distinguishes COVID-19, normal, and pneumonia patient’s X-rays with an accuracy of 92% and AUC score of 98% in the Multi-class classification task. For evaluation on our data set, we fine-tuned some of the widely used models in literature, namely, EfficientNetB0, InceptionV3, Resnet50, MobileNetV3, Xception, and DenseNet-121, as baselines. Our proposed transformer model outperformed them in terms of all metrics. In addition, a Grad-CAM based visualization is created which makes our approach interpretable by radiologists and can be used to monitor the progression of the disease in the affected lungs, assisting healthcare.