Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 May 14:8:91916-91923.
doi: 10.1109/ACCESS.2020.2994762. eCollection 2020.

CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection

Abdul Waheed  1 , Muskan Goyal  1 , Deepak Gupta  1 , Ashish Khanna  1 , Fadi Al-Turjman  2 , Placido Rogerio Pinheiro  3   4
Affiliations

CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection

Abdul Waheed et al. IEEE Access. .

Abstract

Coronavirus (COVID-19) is a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The spread of COVID-19 seems to have a detrimental effect on the global economy and health. A positive chest X-ray of infected patients is a crucial step in the battle against COVID-19. Early results suggest that abnormalities exist in chest X-rays of patients suggestive of COVID-19. This has led to the introduction of a variety of deep learning systems and studies have shown that the accuracy of COVID-19 patient detection through the use of chest X-rays is strongly optimistic. Deep learning networks like convolutional neural networks (CNNs) need a substantial amount of training data. Because the outbreak is recent, it is difficult to gather a significant number of radiographic images in such a short time. Therefore, in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN,the accuracy increased to 95%. We hope this method will speed up COVID-19 detection and lead to more robust systems of radiology.

Keywords: COVID-19 detection; Deep learning; convolutional neural networks; generative adversarial networks; synthetic data augmentation.

PubMed Disclaimer

Figures

FIGURE 1.
FIGURE 1.
ACGAN Architecture.
FIGURE 2.
FIGURE 2.
CovidGAN complete Architecture with generator and discriminator.
FIGURE 3.
FIGURE 3.
Layered Architecture of CovidGAN generator.
FIGURE 4.
FIGURE 4.
A: Real images in dataset, B: Synthetic images generated by CovidGAN.
FIGURE 5.
FIGURE 5.
PCA visualization.
FIGURE 6.
FIGURE 6.
Confusion matrix for Covid-19 detection using CNN with actual data.
FIGURE 7.
FIGURE 7.
Confusion matrix for Covid-19 detection using CNN with synthetic data augmentation and actual data.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Wang S., Sun J., Mehmood I., Pan C., Chen Y., and Zhang Y., “Cerebral micro-bleeding identification based on a nine-layer convolutional neural network with stochastic pooling,” Concurrency Comput., Pract. Exper., vol. 32, no. , p. e5130, Jan. 2020.
    1. Wang S., Tang C., Sun J., and Zhang Y., “Cerebral micro-bleeding detection based on densely connected neural network,” Frontiers Neurosci., vol. 13, p. 422, 2019. - PMC - PubMed
    1. Kang C., Yu X., Wang S.-H., Guttery D., Pandey H., Tian Y., and Zhang Y., “A heuristic neural network structure relying on fuzzy logic for images scoring,” IEEE Trans. Fuzzy Syst., early access, Jan. 13, 2020, doi: 10.1109/TFUZZ.2020.2966163. - DOI - PMC - PubMed
    1. Litjens G., Kooi T., Bejnordi B. E., Setio A. A. A., Ciompi F., Ghafoorian M., van der Laak J. A. W. M., van Ginneken B., and Sánchez C. I., “A survey on deep learning in medical image analysis,” Med. Image Anal., vol. 42, pp. 60–88, Dec. 2017. - PubMed
    1. Roth H. R., Lu L., Liu J., Yao J., Seff A., Cherry K., Kim L., and Summers R. M., “Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1170–1181, May 2016, doi: 10.1109/tmi.2015.2482920. - DOI - PMC - PubMed

LinkOut - more resources