Detection of COVID-19 using Deep Learning with CT Scan Images

Main Article Content

Triratana Metkarunchit
Kiarttipum Charoenpojvajana

Abstract

   The demand of testing the potential infected patient of “new corona virus” or COVID-19 has been enormously increased as the virus is still continuously and immensely spread in many countries. The popular method of testing is to analyze the genetic material of the virus with reverse transcription - polymerase chain reaction (RT-PCR). Recently, the chest x-rays have been introduced to diagnose the infection as it is considered to be easier and crucial method in this circumstance, especially when combine with a deep learning that can recognize and detect the abnormality of lung parenchyma, in which considered to be the signature of COVID-19 effectively. The purpose of this article is to adapt the mask region-based convolutional neural networks (Mask RCNN) to segment the regions that had been affected by the virus by using computed tomography (CT) scan on the chest. The prediction of the tissues regions that have been damaged will help the medical team to classify if the patients are in ‘mild’ or ‘danger’ situation easier. From the model test result processed on google cloud platform, this model F1 scores equivalent to 89% and has the average of speed inference at 9.71 second.

Article Details

Section
Research Article

References

World Health Organization, “WHO coronavirus disease (COVID-19) dashboard,” Accessed: Nov. 10, 2020. [Online]. Available: https://covid19.who.int

F. Pan, T. Ye, P. Sun, S. Gui, B. Liang, L. Li, D. Zheng, J. Wang, R. L. Hesketh, L. Yang, and C. Zheng, “Time course of lung changes at chest CT during recovery from coronavirus disease 2019 (COVID-19),” Radiology, vol. 295, no.3, pp. 715–721, 2020.

S. Basu, S. Mitra, and N. Saha, “Deep learning for screening COVID-19 using chest X-ray Images,” 2020. [Online]. Available: arXiv:2004.10507.

S. Latif, J. Qadir, S. Farooq, and M. A. Imran, “How 5G wireless (and concomitant technologies) will revolutionize healthcare?,” Future Internet, vol. 9, no. 4, pp. 1-24, 2017.

Y. Wang, C. Dong, Y. Hu, C. Li, Q. Ren, X. Zhang, H. Shi, and M. Zhou, “Temporal changes of CT findings in 90 patients with COVID-19 pneumonia:A longitudinal study,” Radiology, vol. 296, no. 2, pp. E55-E64, Mar, 2020.

J. L. He, L. Luo, Z. D. Luo, J. X. Lyu, M. Y. Ng, X. P. Shen, and Z. Wen, “Diagnostic performance between CT and initial real-time RT-PCR for clinically suspected 2019 coronavirus disease (COVID-19) patients outside Wuhan, China,” Respiratory Medicine, vol. 168, pp. 1-5, Apr. 2020.

S. C. Shelmerdine, J. Lovrenski, P. C. Domínguez, and S. Toso, “Coronavirus disease 2019 (COVID-19) in children: A systematic review of imaging findings,” Pediatric Radiology, vol. 50, no. 9, pp. 1217–1230, Jun, 2020.

G. Maguolo and L. Nanni, “A critic evaluation of methods for COVID-19 automatic detection from x-ray images,” 2020. [Online]. Available: arXiv:2004.12823.

F. Shan, Y. Gao, J. Wang, W. Shi, N. Shi, M. Han, Z. Xue, and Y. Shi, “Lung infection quantification of COVID-19 in CT images with deep learning,” 2020. [Online]. Available: arXiv:2003.04655.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” 2018. [Online]. Available: arXiv:1703.06870.

M. Aleem, R. Raj, and A. Khan, “Comparative performance analysis of the ResNet backbones of mask RCNN to segment the signs of COVID-19 in chest CT scans,” 2020. [Online]. Available: arXiv:2008.09713.

J. P. Cohen, P. Morrison, L. Dao, K. Roth, T. Q. Duong, and M. Ghassemi, “COVID-19 image data collection: Prospective predictions are the future,” 2020. [Online]. Available: arXiv:2006.11988.

COVID-19 Database, Società Italiana di Radiologia, Nov. 2020. [Online]. Available: https://www.sirm.org/category/senza-categoria/covid-19

A. Dutta, A. Gupta, and A. Zisserman. VGG Image Annotator. (2020). Access: Nov. 10, 2020. [Online]. Available: http://www.robots.ox.ac.uk/~vgg/software/via