International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

A Deep Learning Approach for Covid-19 Detection in Chest X-Rays

  • Sk. Shalauddin Kabir (Department of Computer Science and Engineering, Jashore University of Science and Technology) ;
  • Syed Galib (Department of Computer Science and Engineering, Jashore University of Science and Technology) ;
  • Hazrat Ali (Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus) ;
  • Fee Faysal Ahmed (Department of Mathematics, Jashore University of Science and Technology) ;
  • Mohammad Farhad Bulbul (Department of Mathematics, Jashore University of Science and Technology)
  • Received : 2024.03.05
  • Published : 2024.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

The novel coronavirus 2019 is called COVID-19 has outspread swiftly worldwide. An early diagnosis is more important to control its quick spread. Medical imaging mechanics, chest calculated tomography or chest X-ray, are playing a vital character in the identification and testing of COVID-19 in this present epidemic. Chest X-ray is cost effective method for Covid-19 detection however the manual process of x-ray analysis is time consuming given that the number of infected individuals keep growing rapidly. For this reason, it is very important to develop an automated COVID-19 detection process to control this pandemic. In this study, we address the task of automatic detection of Covid-19 by using a popular deep learning model namely the VGG19 model. We used 1300 healthy and 1300 confirmed COVID-19 chest X-ray images in this experiment. We performed three experiments by freezing different blocks and layers of VGG19 and finally, we used a machine learning classifier SVM for detecting COVID-19. In every experiment, we used a five-fold cross-validation method to train and validated the model and finally achieved 98.1% overall classification accuracy. Experimental results show that our proposed method using the deep learning-based VGG19 model can be used as a tool to aid radiologists and play a crucial role in the timely diagnosis of Covid-19.

Keywords

References

  1. Zheng, Y.Y.; Ma, Y.T.; Zhang, J.Y.; Xie, X. COVID-19 and the cardiovascular system. Nat. Rev. Cardiol. 2020, 17, 259-260. https://doi.org/10.1038/s41569-020-0360-5
  2. Roosa, K., Lee, Y., Luo, R., Kirpich, A., Rothenberg, R., Hyman, J. M., Yan, P., and Chowell, G. Real-time forecasts of the COVID-19 epidemic in China from February 5th to February 24th, 2020. Infectious Disease Modelling, 5: 256-263, 2020. https://doi.org/10.1016/j.idm.2020.02.002
  3. Cui, J.; Li, F.; Shi, Z.L. Origin and evolution of pathogenic coronaviruses. Nat. Rev. Microbiol. 2019, 17, 181-192. https://doi.org/10.1038/s41579-018-0118-9
  4. Singhal, T. A review of coronavirus disease-2019 (COVID-19). Indian J. Pediatr. 2020, 87, 281-286. https://doi.org/10.1007/s12098-020-03263-6
  5. Momattin, H.; Al-Ali, A.Y.; Al-Tawfiq, J.A. A Systematic Review of therapeutic agents for the treatment of the Middle East Respiratory Syndrome Coronavirus (MERS-CoV). Travel Med. Infect. Dis. 2019, 30, 9-18. https://doi.org/10.1016/j.tmaid.2019.06.012
  6. Available: https://www.worldometers.info/coronavirus/?utm_campaign=homeADemocracynow(2020)%20dvegas1?[Accessed 12 March 2021].
  7. Huang, C.; Wang, Y.; Li, X.; Ren, L.; Zhao, J.; Hu, Y.; Zhang, L.; Fan, G.; Xu, J.; Gu, X.; et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet 2020, 395, 497-506. https://doi.org/10.1016/S0140-6736(20)30183-5
  8. "Coronavirus disease (COVID-19): How is it transmitted?". World Health Organization (WHO). Retrieved 6 December 2020.
  9. Mahase, E. Coronavirus: covid-19 has killed more people than SARS and MERS combined, despite lower case fatality rate. The BMJ, 368: m641, doi: 10.1136/bmj.m641, 2020.
  10. Ai, T., Yang, Z., Hou, H., Zhan, C., Chen, C., Lv, W., Tao, X., Sun, Z., and Xia, L. Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases. Radiology, 200642: 1-23, https://doi.org/10.1148/radiol.2020200642, 2020.
  11. Zhai, P.; Ding, Y.; Wu, X.; Long, J.; Zhong, Y.; Li, Y. The epidemiology, diagnosis and treatment of COVID-19. Int. J. Antimicrob. Agents 2020, 55, 105955.
  12. Zhang, W. Imaging changes of severe COVID-19 pneumonia in advanced stage. Intensive care medicine, 1-3, https://doi.org/10.1007/s00134-020-05990-y, 2020.
  13. Fang, Y.; Zhang, H.; Xie, J.; Lin, M.; Ying, L.; Pang, P.; Ji,W. Sensitivity of chest CT for COVID-19: Comparison to RT-PCR. Radiology 2020, 92, 200432.
  14. Lin, E.C. Radiation risk from medical imaging. In Mayo Clinic Proceedings; Elsevier: Amsterdam, The Netherlands, 2010; Volume 85, pp. 1142-1146.
  15. Self,W.H.; Courtney, D.M.; McNaughton, C.D.;Wunderink, R.G.; Kline, J.A. High discordance of chest X-rayand computed tomography for detection of pulmonary opacities in ED patients: Implications for diagnosing pneumonia. Am. J. Emerg. Med. 2013, 31, 401-405. https://doi.org/10.1016/j.ajem.2012.08.041
  16. Jacobi, A.; Chung, M.; Bernheim, A.; Eber, C. Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review. Clin. Imaging 2020, 64, 35-42. https://doi.org/10.1016/j.clinimag.2020.04.001
  17. Ratnapalan, S.; Bentur, Y.; Koren, G. Doctor, will that X-ray harm my unborn child? Cmaj 2008, 179, 1293-1296. https://doi.org/10.1503/cmaj.080247
  18. Gozes, O., Frid-Adar, M., Greenspan, H., Browning, P. D., Zhang, H., Ji, W., Bernheim, A., and Siegel, E. Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for Automated Detection & Patient Monitoring using Deep Learning CT Image Analysis. arXiv preprint arXiv:2003.05037, 1-19, 2020.
  19. Shan, F., Gao, Y., Wang, J., Shi, W., Shi, N., Han, M., Xue, Z., and Shi, Y. Lung Infection Quantification of COVID-19 in CT Images with Deep Learning. arXiv preprint arXiv:2003.04655, 1-19, 2020.
  20. Xu, X., Jiang, X., Ma, C., Du, P., Li, X., Lv, S., Yu, L., Chen, Y., Su, J., Lang, G., Li, Y., Zhao, H., Xu, K., Ruan, L., and Wu, W. Deep Learning System to Screen Coronavirus Disease 2019 Pneumonia. arXiv preprint arXiv:2002.09334, 1-29, 2020.
  21. Wang, S., Kang, B., Ma, J., Zeng, X., Xiao, M., Guo, J., Cai, M., Yang, J., Li, Y., Meng, X., and Xu, B. A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19). medRxiv preprint doi: https://doi.org/10.1101/2020.02.14.20023028, 1-26, 2020.
  22. Detecting COVID-19 in X-ray Images with Keras, TensorFlow, and Deep Learning. Available online: https://www.pyimagesearch.com/2020/03/16/detecting-covid-19-in-x-ray-images-with-keras-tensorflowand-deep-learning/ [Accessed 16 January 2021].
  23. Cohen, J.P.; Morrison, P.; Dao, L. COVID-19 Image Data Collection. arXiv 2020, arXiv:2003.11597v1.
  24. Hemdan, E.E.D.; Shouman, M.A.; Karar, M.E. COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-ray Images. arXiv 2020, arXiv:2003.11055.
  25. Narin, A.; Kaya, C.; Pamuk, Z. Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. arXiv 2020, arXiv:2003.10849.
  26. Sethy, P. K., and Behera, S. K. Detection of coronavirus Disease (COVID-19) based on Deep Features. Preprints 2020, 2020030300, doi: 10.20944/preprints202003.0300.v1).
  27. Zhang, J.; Xie, Y.; Li, Y.; Shen, C.; Xia, Y. COVID-19 screening on chest X-ray images using deep learning based anomaly detection. arXiv 2020, arXiv:2003.12338.
  28. Wang, L.;Wong, A. COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-ray Images. arXiv 2020, arXiv:2003.09871.
  29. COVID-19 Chest X-ray Dataset Initiative. Available online: https://github.com/agchung/Figure1-COVIDchestxraydataset[Accessed 16 January 2021].
  30. RSNA Pneumonia Detection Challenge. Available online: https://www.kaggle.com/c/rsna-pneumoniadetection-challenge/data [Accessed 16 January 2021].
  31. Actualmed-COVID-chestxray-dataset. Available online: https://github.com/agchung/ActualmedCOVIDchestxray-dataset [Accessed 17 January 2021].
  32. COVID-19 Radiography Database. Available online: https://www.kaggle.com/tawsifurrahman/covid19-radiography-database [Accessed 17 January 2021].
  33. Ozturk, T.; Talo, M.; Yildirim, E.A.; Baloglu, U.B.; Yildirim, O.; Acharya, U.R. Automated detection ofCOVID-19 cases using deep neural networks with X-ray images. Comput. Boil. Med. 2020, 121, 103792.
  34. Wang, X.; Peng, Y.; Lu, L.; Lu, Z.; Bagheri, M.; Summers, R.M. ChestX-ray8: Hospital-scale chest X-raydatabase and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21-26 July 2017; pp. 3462-3471.
  35. Cohen, J.P.; Morrison, P.; Dao, L. COVID-19 Image Data Collection. arXiv 2020, arXiv:2003.11597v1.
  36. Afshar, P.; Heidarian, S.; Naderkhani, F.; Oikonomou, A.; Plataniotis, K.N.; Mohammadi, A. COVID-CAPS: A Capsule Network-based Framework for Identification of COVID-19 cases from X-ray Images. arXiv 2020, arXiv:2004.02696.
  37. Chest X-ray Images (Pneumonia). Available online: https://www.kaggle.com/paultimothymooney/chestxray-pneumonia [Accessed 17 January 2021].
  38. Oh, Y.; Park, S.; Ye, J.C. Deep Learning COVID-19 Features on CXR using Limited Training Data Sets. IEEE Trans. Med. Imaging 2020, 39, 2688-2700. https://doi.org/10.1109/TMI.2020.2993291
  39. Jaeger, S.; Candemir, S.; Antani, S.;Wang, Y.-X.J.; Lu, P.-X.; Thoma, G. Two public chest X-ray datasets forcomputer-aided screening of pulmonary diseases. Quant. Imaging Med. Surg. 2014, 4, 475-477.
  40. CoronaHack-Chest X-ray-Dataset. Available online: https://www.kaggle.com/praveengovi/coronahackchest-xraydataset [Accessed 17 January 2021].
  41. Shiraishi, J.; Katsuragawa, S.; Ikezoe, J.; Matsumoto, T.; Kobayashi, T.; Komatsu, K.-I.; Matsui, M.; Fujita, H.; Kodera, Y.; Doi, K. Development of a Digital Image Database for Chest Radiographs with and without a Lung Nodule. Am. J. Roentgenol. 2000, 174, 71-74. https://doi.org/10.2214/ajr.174.1.1740071
  42. Van Ginneken, B.; Stegmann, M.B.; Loog, M. Segmentation of anatomical structures in chest radiographsusing supervised methods: A comparative study on a public database. Med. Image Anal. 2006, 10, 19-40. https://doi.org/10.1016/j.media.2005.02.002
  43. COVID-19 Chest X-ray Database. Available online: https://github.com/ieee8023/covid-chestxray-dataset [Accessed 18 January 2021].
  44. Normal Chest X-ray Database. Available online: https://www.kaggle.com/paultimothymooney/chest-xray-Pneumonia [Accessed 18 January 2021].
  45. COVID-19 Chest X-ray Dataset Initiative. Available online: https://github.com/agchung/Figure1-COVIDchestxray-dataset [Accessed 18 January 2021].
  46. Vaya, M.d.l.I.; Saborit, J.M.; Montell, J.A.; Pertusa, A.; Bustos, A.; Cazorla, M.; Galant, J.; Barber, X.; Orozco-Beltran, D.; Garcia, F.; et al. BIMCV COVID-19+: A large annotated dataset of RX and CT images from COVID-19 patients. arXiv 2020, arXiv:2006.01174. Available online: https://bimcv.cipf.es/bimcvprojects/bimcv-covid19/[Accessed 18 January 2021].
  47. Bustos, A.; Pertusa, A.; Salinas, J.M.; de la Iglesia-Vaya, M. Padchest: A large chest X-ray image dataset with multi-label annotated reports. arXiv 2019, arXiv:1901.07441. Available online: https://bimcv.cipf.es/bimcvprojects/[Accessed 18 January 2021].
  48. Guendel S, Ghesu FC, Grbic S, Gibson E, Georgescu B, Maier A, Comaniciu D (2019) Multi-task learning for chest x-ray abnormality classification on noisy labels. arXiv:1905.06362
  49. Stephen O, Sain M, Maduh UJ, Jeong DU (2019) An efficient deep learning approach to pneumonia classification in healthcare. Journal of healthcare engineering.
  50. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):60
  51. Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7-9 May 2015; pp. 1-14.