COVIDDCGAN: Oversampling Model Using DCGAN Network to Balance a COVID-19 Dataset

The COVID-19 infection was announced as a pandemic in late 2019. Due to the high speed of the spread, rapid diagnosis can prevent the virus outbreak. Detection of the virus using prominent information from CT scan images is a fast, cheap, and accessible method. However, these image datasets are imbalanced due to the nature of medical data and the lack of coronavirus images. Consequently, the conventional classification algorithms classify this data unsuitably. Oversampling technique is one of the most well-known methods that try to balance the dataset by increasing the minority class of the data. This paper presents a new oversampling model using an improved deep convolutional generative adversarial network (DCGAN) to produce samples that improve classifier performance. In previous DCGAN structures, the feature extraction took place only in the convolution layer, while in the proposed structure, it is done in both the convolution layer and the pooling layer. A Haar transform layer as the pooling layer tries to extract better features. Evaluation results on two hospital datasets express an accuracy of 95.8 and a loss criterion of 0.5354 for the suggested architecture. Moreover, compared to the standard DCGAN structure, the proposed model has superiority in all classification criteria. Therefore, the new model can assist radiologists in validating the initial screening.

A novel deep learning based method for COVID-19 detection from CT image.

The novel Coronavirus named COVID-19 that World Health Organization (WHO) announced as a pandemic rapidly spread worldwide. Fast diagnosis of the virus infection is critical to prevent further spread of the virus, help identify the infected population, and cure the patients. Due to the increasing rate of infection and the limitations of the diagnosis kit, auxiliary detection tools are needed. Recent studies show that a deep learning model that comes up with the salient information of CT images can aid in the COVID-19 diagnosis. This study proposes a novel deep learning structure that the pooling layer of this model is a combination of pooling and the Squeeze Excitation Block (SE-block) layer. The proposed model uses Batch Normalization and Mish Function to optimize convergence time and performance of COVID-19 diagnosis. A dataset of two public hospitals was used to evaluate the proposed model. Moreover, it was compared to some different popular deep neural networks (DNN). The results expressed an accuracy of 99.03 with a recognition time of test mode of 0.069 ms in graphics processing unit (GPU). Furthermore, the best network results in classification metrics parameters and real-time applications belong to the proposed model.