Abstract
Across the world, many people are affected with the outbreak of Coronavirus or COVID–19, since early 2020. The major organ where the viral strain infects is primarily the lungs which brings about a shortness of breath as reported in cases worldwide. At this juncture, we have not been able to find the vaccine or even a clinically approved cure that would help curb the same. Many cases were reported recently, which has grown in an exponential fashion across the world and claimed many lives too. We worked with a substantially small medically approved dataset with clinical correlation of the patient’s condition as was available and tried a deep learning model, a network using the VGG16 network with weights pre-trained on ImageNet dataset and fine-tuned the architecture with our training data so as to suit our need of detection based on the chest X-ray images as to whether the concerned individual has been affected with COVID–19 or not. With limited amount of data that we trained the model with, an accuracy of about 90% was achieved which may well vary as a larger sized training dataset, once available, could be fed into the proposed convolutional neural network architecture model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
https://www.worldometers.info/coronavirus/coronavirus-cases/ As accessed on 1643 hours GMT, dated 24th March, 2020
https://www.worldometers.info/coronavirus/#countries As accessed on 1643 hours GMT, dated 24th March, 2020
Pasa, F., Golkov, V., Pfeiffer, F., et al.: Efficient deep network architectures for fast chest X-ray Tuberculosis screening and visualization. Sci. Rep. 9, 6268 (2019). https://doi.org/10.1038/s41598-019-42557-4
Lakhani, Paras, Sundaram, Baskaran: Deep learning at chest radiography: automated classification of pulmonary Tuberculosis by using convolutional neural networks. Radiology 284, 162326 (2017). https://doi.org/10.1148/radiol.2017162326
Deep Learning for Automated Classification of Tuberculosis-Related Chest X-Ray: Dataset Specificity Limits Diagnostic Performance Generalizability, Seelwan Sathitratanacheewin, Pongpirul
Hwang, S., Kim, H., Jeong, J., Kim, H.: A novel approach for Tuberculosis screening based on deep convolutional neural networks. Proc. SPIE 9785, 1–8 (2016)
Baltruschat, I.M., Nickisch, H., Grass, M., et al.: Comparison of deep learning approaches for multi-label chest X-ray classification. Sci. Rep. 9, 6381 (2019). https://doi.org/10.1038/s41598-019-42294-8
Islam, M.T., Aowal, M.A., Minhaz, A.T., Ashraf, K.: Abnormality detection and localization in chest X-rays using deep convolutional neural networks. CoRR abs/1705.0 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ray, A., Ray, H. (2021). COVID–19 Detection from Chest X-Ray Images Using Deep Learning Techniques. In: Hassanien, A.E., Bhattacharyya, S., Chakrabati, S., Bhattacharya, A., Dutta, S. (eds) Emerging Technologies in Data Mining and Information Security. Advances in Intelligent Systems and Computing, vol 1300. Springer, Singapore. https://doi.org/10.1007/978-981-33-4367-2_63
Download citation
DOI: https://doi.org/10.1007/978-981-33-4367-2_63
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4366-5
Online ISBN: 978-981-33-4367-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)