Abstract
COVID-19 is an infectious disease caused by the novel coronavirus (SARS-COV-2). The global total number of cases is 618 million, leading to 6.5 million deaths by October 2022. As this disease is highly contagious, diagnosis and necessary measures to prevent its spread, including quarantine, must be done early. To help with diagnosis and screening, we propose a deep learning solution that leverages CT images. This solution is based on a new methodology for image pre-processing that focuses on improving image characteristics, combined with data augmentation, transfer of learning and fine-tuning of the model. Of the three convolutional neural networks used - ResNet101, VGG19 and InceptionV3 - the ResNet101 model had the best performance, reaching 98% Precision, 96.84% Kappa, 97.78% Precision, 97.55% Sensitivity and 97.70% F1-Score. The promising results demonstrate that the proposed method can help specialists to detect this disease.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organization. Coronavirus disease (covid-19). Accessed Oct. 18, 2022
World Health Organization. Weekly epidemiological update on covid-19 - 12 october 2022. Accessed Oct. 12, 2022
Kazimierczuk, M., Jozwik, J.: Analysis and design of class e zero-current-switching rectifier. IEEE Trans. Circuits Syst. 37(8) (1990)
Wang, W., Yanli, X., Gao, R., Roujian, L., Han, K., Guizhen, W., Tan, W.: Detection of sars-cov-2 in different types of clinical specimens. JAMA 323(18), 1843–1844 (2020)
ACR: Amemrican College of Radiologyion. Acr recommendations for the use of chest radiography and computed tomography (ct) for suspected covid-19 infection. Accessed Oct. 10, 2022
Godet, C., Elsendoorn, A., Roblot, F.: Benefit of ct scanning for assessing pulmonary disease in the immunodepressed patient. Diagn. Interv. Imaging 93(6), 425–430 (2012)
Rosa, M.E.E., et al.: Covid-19 findings identified in chest computed tomography: a pictorial essay. Einstein (Sao Paulo, Brazil) 18, eRW5741–eRW5741 (2020)
Seum, A., Raj, A., Sakib, S., Hossain, T.: A comparative study of cnn transfer learning classification algorithms with segmentation for covid-19 detection from ct scan images. In: International Conference on Electrical and Computer Engineering, pp. 234–237 (2020)
Kai, H., Huang, Y., Huang, W., Tan, H., Chen, Z., Zhong, Z., Li, X., Zhang, Y., Gao, X.: Deep supervised learning using self-adaptive auxiliary loss for covid-19 diagnosis from imbalanced ct images. Neurocomputing 458, 232–245 (2021)
Cai, X., Wang, Y., Sun, X., Liu, W., Tang, Y., Li, W.: Comparing the performance of resnets on covid-19 diagnosis using ct scans. In: 2020 International Conference on Computer, Information and Telecommunication Systems (CITS), pp. 1–4 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Zhao, J., Zhang, Y., He, X., Xie, P.: . Covid-ct-dataset: A CT scan dataset about COVID-19. CoRR, abs/2003.13865 (2020)
Soares, E., Angelov, P., Biaso, S., Froes, M.H., Abe, D.K.: Sars-cov-2 ct-scan dataset: A large dataset of real patients ct scans for sars-cov-2 identification. medRxiv (2020)
Zhang, Y., Satapathy, S.C., Zhu, L.-Y., Górriz, J.M., Wang, S.: A seven-layer convolutional neural network for chest ct-based covid-19 diagnosis using stochastic pooling. IEEE Sensors J. 22(18), 17573–17582 (2022)
Rahimzadeh, M., Attar, A., Sakhaei, S.M.: A fully automated deep learning-based network for detecting covid-19 from a new and large lung ct scan dataset. Biomed. Signal Process. Control 68, 102588 (2021)
Gunraj, H., Wang, L., Wong, A.: Covidnet-ct: a tailored deep convolutional neural network design for detection of covid-19 cases from chest ct images. Front. Med. 7, 608525–608525 (2020)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv e-prints, arXiv:1409.1556 (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)
Vieira, P., Sousa, O., Magalhães, D., Rabêlo, R., Silva, R.: Detecting pulmonary diseases using deep features in x-ray images. Pattern Recogn. 119, 108081–108081 (2021)
Chollet, F., et al.: Keras (2015)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017)
Acknowledgments
This work was carried out with the full support of the Coordination for the Improvement of Higher Education Personnel - Brazil (CAPES) - Financial Code 001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Marques, J.V.M., de Araújo Gonçalves, C., de Carvalho Ferreira, J.F., de Melo Souza Veras, R., de Andrade Lira Rabelo, R., Veloso e Silva, R.R. (2023). Detection of COVID-19 in Computed Tomography Images Using Deep Learning. In: Abraham, A., Pllana, S., Casalino, G., Ma, K., Bajaj, A. (eds) Intelligent Systems Design and Applications. ISDA 2022. Lecture Notes in Networks and Systems, vol 717. Springer, Cham. https://doi.org/10.1007/978-3-031-35510-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-35510-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35509-7
Online ISBN: 978-3-031-35510-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)