COVID-CGAN: Efficient Deep Learning Approach for COVID-19 Detection Based on CXR Images Using Conditional GANs

Abstract

COVID-19, a novel coronavirus infectious disease, has spread around the world, resulting in a large number of deaths. Due to a lack of physicians, emergency facilities, and equipment, medical systems have been unable to treat all patients in many countries. Deep learning is a promising approach for providing solutions to COVID-19 based on patients’ medical images. As COVID-19 is a new disease, its related dataset is still being collected and published. Small COVID-19 datasets may not be sufficient to build powerful deep learning detection models. Such models are often over-fitted, and their prediction results cannot be generalized. To fill this gap, we propose a deep learning approach for accurately detecting COVID-19 cases based on chest X-ray (CXR) images. For the proposed approach, named COVID-CGAN, we first generated a larger dataset using generative adversarial networks (GANs). Specifically, a customized conditional GAN (CGAN) was designed to generate the target COVID-19 CXR images. The expanded dataset, which contains 84.8% generated images and 15.2% original images, was then used for training five deep detection models: InceptionResNetV2, Xception, SqueezeNet, VGG16, and AlexNet. The results show that the use of the synthetic CXR images, which were generated by the customized CGAN, helped all deep learning models to achieve high detection accuracies. In particular, the highest accuracy was achieved by the InceptionResNetV2 model, which was 99.72% accurate with only ten epochs. All five models achieved kappa coefficients between 0.81 and 1, which is interpreted as an almost perfect agreement between the actual labels and the detected labels. Furthermore, the experiment showed that some models were faster yet smaller compared to the others but could still achieve high accuracy. For instance, SqueezeNet, which is a small network, required only three minutes and achieved comparable accuracy to larger networks such as InceptionResNetV2, which needed about 143 min. Our proposed approach can be applied to other fields with scarce datasets.