School of Electronics Engineering, KIIT Deemed to be University, Odisha 751024, India.
Department of Computer Science & Engineering, Vardhaman College of Engineering (Autonomous), Hyderabad 501218, India.
Int J Environ Res Public Health. 2021 Oct 21;18(21):11086. doi: 10.3390/ijerph182111086.
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.
在最近的大流行中，对患者进行准确和快速的检测仍然是医疗保健行业诊断和控制 COVID-19 疾病传播的关键任务。由于病例的突然增加，大多数国家都面临着检测的稀缺和低速度。文献表明，胸部 X 光检查是 COVID-19 患者检测的潜在来源，但手动检查 X 光报告既耗时又容易出错。考虑到这些限制因素和数据科学的进步，我们提出了一种基于 Vision Transformer 的深度学习管道，用于从基于胸部 X 光的成像中检测 COVID-19。由于缺乏大型数据集，我们从三个开源的胸部 X 光图像数据集收集数据，并将其聚合形成一个 30 K 图像数据集，据我们所知，这是该领域最大的公开胸部 X 光图像数据集。我们提出的变换模型能够有效地将 COVID-19 与正常的胸部 X 光区分开来，在二分类任务中的准确率为 98%，AUC 评分为 99%。在多分类任务中，它能够准确地区分 COVID-19、正常和肺炎患者的 X 光，准确率为 92%，AUC 评分为 98%。为了在我们的数据集中进行评估，我们对文献中一些广泛使用的模型进行了微调，即 EfficientNetB0、InceptionV3、Resnet50、MobileNetV3、Xception 和 DenseNet-121，作为基准模型。与它们相比，我们提出的变换模型在所有指标上都表现出色。此外，还创建了一个基于 Grad-CAM 的可视化，使我们的方法可由放射科医生解释，并可用于监测受影响肺部疾病的进展，辅助医疗保健。
