Page 113 - IJEEE-2022-Vol18-ISSUE-1
P. 113
Majid & Ali | 109
VII. CONCLUSIONS Images with Pathology,” pp. 1–16, 2019, [Online].
The world was attacked by a novel coronavirus in late 2019 Available: http://arxiv.org/abs/1911.08716.
that caused death and infected millions of people in just a
few months, to prevent the spread of the virus we need early [12] A. L. Barbieri, O. Fadare, L. Fan, H. Singh, and V.
detection as a result we proposed a deep learning approach Parkash, “Challenges in communication from referring
based on traditional augmentation and Conditional
Generative Adversarial Networks (CGAN) to expending clinicians to pathologists in the electronic health record
limited COVID-19 dataset, the CGAN Technique could era,” J. Pathol. Inform., vol. 9, no. 1, 2018, doi:
generate realistic synthetic COVID-19 X-ray images that
have never been seen previously by learning the distribution 10.4103/jpi.jpi.
noise of images, our dataset expanding from 587 to 6988 [13] T. Han et al., “Breaking medical data sharing
with high-quality images and variety. The augmented dataset
improves the performance of the customized detection model boundaries by using synthesized radiographs,” Sci. Adv.,
and resolves the overfitting issue. The experiment showed
that the deep learning model can significantly improve the vol. 6, no. 49, 2020, doi: 10.1126/sciadv.abb7973.
speed diagnosing of COVID-19 cases with high accuracy of
97%. [14] A. Waheed, M. Goyal, D. Gupta, A. Khanna, F. Al-
Turjman, and P. R. Pinheiro, “CovidGAN: Data
CONFLICT OF INTEREST
Augmentation Using Auxiliary Classifier GAN for
The authors have no conflict of relevant interest to this Improved Covid-19 Detection,” IEEE Access, vol. 8, pp.
article. 91916–91923, 2020.
REFERENCES doi: 10.1109/ACCESS.2020.2994762.
[15] M. Loey, G. Manogaran, N. Eldeen, and M. Khalifa, “A
[1] L. Chang, Y. Yan, and L. Wang, “Coronavirus Disease
2019: Coronaviruses and Blood Safety,” Transfus. Med. Deep Transfer Learning Model with Classical Data
Rev., vol. 34, no. 2, pp. 75–80, 2020, doi:
10.1016/j.tmrv.2020.02.003. Augmentation and CGAN to Detect COVID-19 from
Chest CT Radiography Digital Images,” 2020. [Online].
[2] "Johns Hopkins coronavirus resource center,"
https://coronavirus.jhu.edu/ map.html Available: https://www.medrxiv.org.
[3] M. A. Shereen, S. Khan, A. Kazmi, N. Bashir, and R. [16] A. A. Al-Shargabi, J. F. Alshobaili, A. Alabdulatif, and
Siddique, “COVID-19 infection: Origin, transmission, and N. Alrobah, “Covid-cgan: Efficient deep learning
characteristics of human coronaviruses,” J. Adv. Res., vol.
24, pp. 91–98, 2020, doi: 10.1016/j.jare.2020.03.005. approach for covid-19 detection based on cxr images using
conditional gans,” Appl. Sci., vol. 11, no. 16, Aug. 2021,
[4] "Centers of disease control and prevention,"
https://www.cdc.gov/ doi: 10.3390/app11167174.doi: 10.3390/app11167174
[5] W. Guan et al., “Clinical Characteristics of Coronavirus [17] M. A. Zulkifley, S. R. Abdani, and N. H. Zulkifley,
Disease 2019 in China,” N. Engl. J. Med., vol. 382, no. 18, “COVID-19 screening using a lightweight convolutional
pp. 1708–1720, 2020, doi: 10.1056/nejmoa2002032.
neural network with generative adversarial network data
[6] “Interim clinical guidance for management of patients augmentation,” Symmetry (Basel)., vol. 12, no. 9, Sep.
with confirmed coronavirus disease (covid-19),”
https://www.cdc.gov/coronavirus/2019-ncov/hcp/clinical- 2020, doi: 10.3390/SYM12091530.
guidance-management-patients.html. [18] Y. Jiang, H. Chen, M. Loew, and H. Ko, “COVID-19
[7] Y. Fang and P. Pang, “Senivity of Chest CT for CT Image Synthesis with a Conditional Generative
COVID.19: Comparasion to RT.PCR,” Radiology, vol. Adversarial Network,” IEEE J. Biomed. Heal. Informatics,
296, pp. 15–17, 2020. vol. 25, no. 2, pp. 441–452, 2021, doi:
[8] X. Yi, E. Walia, and P. Babyn, “Generative adversarial 10.1109/JBHI.2020.3042523.
network in medical imaging: A review,” Med. Image
Anal., vol. 58, 2019, doi: 10.1016/j.media.2019.101552. [19] H. Alqahtani, M. Kavakli-Thorne, and G. Kumar,
“Applications of Generative Adversarial Networks
[9] M. Krithika alias Anbu Devi and K. Suganthi, “Review (GANs): An Updated Review,” Arch. Comput. Methods
of Medical Image Synthesis using GAN Techniques,” ITM Eng., vol. 28, no. 2, pp. 525–552, 2021, doi:
Web Conf., vol. 37, p. 01005, 2021, doi:
10.1051/itmconf/20213701005. 10.1007/s11831-019-09388-y.
[20] M. Krithika alias Anbu Devi and K. Suganthi, “Review
[10] H. P. Das et al., “Conditional Synthetic Data Generation
for Robust Machine Learning Applications with Limited of Medical Image Synthesis using GAN Techniques,” ITM
Pandemic Data,” Sep. 2021, [Online]. Available:
http://arxiv.org/abs/2109.06486. Web Conf., vol. 37, p. 01005, 2021, doi:
[11] A. Ghorbani, V. Natarajan, D. Coz, and Y. Liu, 10.1051/itmconf/20213701005.
“DermGAN: Synthetic Generation of Clinical Skin [21] X. Yi, E. Walia, and P. Babyn, “Generative adversarial
network in medical imaging: A review,” Med. Image
Anal., vol. 58, 2019, doi: 10.1016/j.media.2019.101552.
[22] M. Mirza and S. Osindero, “Conditional Generative
Adversarial Nets,” Nov. 2014, [Online]. Available:
http://arxiv.org/abs/1411.1784.
[23] J. A. Rodríguez de la Cruz, H. G. Acosta Mesa, E.
Mezura Montes, F. Arámbula Cosío, B. Escalante
Ramírez, and J. Olveres Montiel, “Evolution of
conditional-GANs for the synthesis of chest x-ray
images,” no. December, p. 50, 2021, doi:
10.1117/12.2606272.
[24] https://www.kaggle.com/c/rsna-pneumonia-detection-
challenge/data
[25] https://bimcv.cipf.es/bimcv-projects/bimcv-covid19/#
