International Journal of Computer Science & Network Security

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

DOI QR Code

Enhanced CT-image for Covid-19 classification using ResNet 50

  • Lobna M. Abouelmagd (MET Misr higher institute, Computer Science Department) ;
  • Manal soubhy Ali Elbelkasy (High institute of technology and management - kafer elsheikh)
  • Received : 2024.01.05
  • Published : 2024.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

Disease caused by the coronavirus (COVID-19) is sweeping the globe. There are numerous methods for identifying this disease using a chest imaging. Computerized Tomography (CT) chest scans are used in this study to detect COVID-19 disease using a pretrain Convolutional Neural Network (CNN) ResNet50. This model is based on image dataset taken from two hospitals and used to identify Covid-19 illnesses. The pre-train CNN (ResNet50) architecture was used for feature extraction, and then fully connected layers were used for classification, yielding 97%, 96%, 96%, 96% for accuracy, precision, recall, and F1-score, respectively. When combining the feature extraction techniques with the Back Propagation Neural Network (BPNN), it produced accuracy, precision, recall, and F1-scores of 92.5%, 83%, 92%, and 87.3%. In our suggested approach, we use a preprocessing phase to improve accuracy. The image was enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, which was followed by cropping the image before feature extraction with ResNet50. Finally, a fully connected layer was added for classification, with results of 99.1%, 98.7%, 99%, 98.8% in terms of accuracy, precision, recall, and F1-score.

Keywords

References

  1. World Health Organization, https://www.who.int, last access November 2021.
  2. Mohamed Mohamed Hefed, "CT chest findings in patients infected with COVID-19: review of literature", Egyptian Journal of Radiology and Nuclear Medicine (2020) 51:239. doi.org/10.1186/s43055-020-00355-3.
  3. Ohad Oren, Bernard J Gersh and Deepak L Bhatt, "Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints", Lancet Digital Health 2020; 2: e486-488, Vol 2 September 2020. doi.org/10.1016/S2589-7500(20)30160-6.
  4. Sarker and I.H., "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions", SN COMPUT. SCI. 2, 420 (2021). doi.org/10.1007/s42979-021-00815-1.
  5. S. Khan, and S. P. Yong, "A deep learning architecture for classifying medical images of anatomy object," Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, pp. 1661-1668, 2018.
  6. Yong Wu,Xiao Qin, Yonghua Pan, and Changan Yuan, "Convolution Neural Network based Transfer Learning for Classification of Flowers", IEEE 3rd International Conference on Signal and Image Processing ,2018.
  7. Simonyan K, and Zisserman A. "Very Deep Convolutional Networks for Large-Scale Image Recognition". Computer Science, 2014.
  8. He K., Zhang X., Ren S. and Sun J. "Deep residual learning for image recognition". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770-778, 2016.
  9. He Kaiming, Zhang Xiangyu, Ren Shaoqing, and Sun Jian, "Deep Residual Learning for Image Recognition", arXiv:1512.03385, 2015
  10. Veit Andreas, Wilber Michael and Belongie Serge, "Residual Networks Behave Like Ensembles of Relatively Shallow Networks", arXiv:1605.06431, 2016.
  11. Sonali , Sima Sahu , Amit Kumar Singh, S.P. Ghrera , and Mohamed Elhoseny, " An approach for de-noising and contrast enhancement of retinal fundus image using CLAHE ",Opt. Laser Technol. 2018, https://doi.org/10.1016/j.optlastec.2018.06.061.
  12. Maison, T Lestari and A Luthfi, "Retinal Blood Vessel Segmentation using Gaussian Filter", Journal of Physics: Conference Series, 1376 (2019) 012023. doi:10.1088/1742-6596/1376/1/012023.
  13. Yann LeCun et al., "GradientBased Learning Applied to Document Recognition", In Proc. Of the IEEE NOVEMBER 1998.
  14. Lobna M. Abou El-Maged, Ashraf Darwish, and Aboul Ella Hassanien, "Artificial Intelligence-Based Plant's Diseases Classification", Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020), 2020, Volume 1153.
  15. Sajja Tulasi Krishna, and Hemantha Kumar Kallur, " Deep Learning and Transfer Learning Approaches for Image Classification", International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-7, Issue5S4, February 2019.
  16. A. Sai Bharadwaj Reddy and D. Sujitha Juliet, "Transfer Learning with ResNet-50 for Malaria Cell-Image Classification", International Conference on Communication and Signal Processing, April 4-6, 2019, India.
  17. Jin Hong, Hong Cheng, Yu-Dong Zhang, and Jie Liu, "Detecting cerebral microbleeds with transfer learning", Machine Vision and Applications (2019) 30:1123-1133. https://doi.org/10.1007/s00138-019-01029-5
  18. Edmar Rezende, Guilherme Ruppert, Tiago Carvalho, Fabio Ramos, and Paulo de Geus, "Malicious Software Classification using Transfer Learning of ResNet-50 Deep Neural Network", 2017 16th IEEE International Conference on Machine Learning and Applications, 2017.
  19. J Praveen Gujjar , H R Prasanna Kumar and Niranjan N. Chiplunkar , " Image classification and prediction using transfer learning in colab notebook", Global Transitions Proceedings 2 (2021) 382-385, https://doi.org/10.1016/j.gltp.2021.08.068
  20. Asghar Azizi1, SeyyedZioddin Shafaei, Reza Rooki, Ahmad Hasanzadeh and Mostafa Paymard, "Estimating of gold recovery by using back propagation neural network and multiple linear regression methods in cyanide leaching process", MSAIJ, 8(11), [443-453], 2012.
  21. Ul-Saufie, A.Z., Yahya, A.S.,Ramli, N.A., Hamid, H.A., "Comparison between multiple linear regression and feed forward back propagation neural network models for predicting PM10 concentration level based on gaseous and meteorological parameters", Int. J. Sci. Tech., 1: 42-49, 2011.
  22. https://europepmc.org/article/ppr/ppr141530
  23. M. N. J. R and K. Balaji, "Performance Analysis of Neural Networks and Support Vector Machines using Confusion Matrix", International Journal of Advanced Research in Science, Engineering and Technology (IJARSET) vol. 3, no. 5, pp. 2106-2109, 2016.
  24. Kingma, D. P., and Ba, J. L., "Adam: a Method for Stochastic Optimization. International Conference on Learning Representations", Published as a conference paper at ICLR 2015
  25. Y. Pathak, P.K. Shukla, A. Tiwari, S. Stalin, S. Singh and P.K. Shukla, "Deep transfer learning based classification model for COVID-19 disease", IRBM (2020) http://dx.doi.org/10.1016/j.irbm.2020.05.003.
  26. H. Kang, L. Xia, F. Yan, Z. Wan, F. Shi, H. Yuan, et al., Diagnosis of coronavirus disease 2019 (COVID-19) with structured latent multi-view representation learning, IEEE. Trans. Med. Imaging (2020) http://dx.doi.org/10.1109/TMI.2020.2992546.
  27. X. Wang, X. Deng, Q. Fu, Q. Zhou, J. Feng, H. Ma, et al., "A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT", IEEE Trans. Med. Imaging 1 (2020) http://dx.doi.org/10.1109/TMI.2020.2995965.
  28. Samir Elmuogy, Noha A. Hikal, and Esraa Hassan, "An efficient technique for CT scan images classification of COVID-19", Journal of Intelligent & Fuzzy Systems 40 (2021) 5225-5238 . DOI:10.3233/JIFS-201985.
  29. Kai Gao , Jianpo Su , Zhongbiao Jiang , Ling-Li Zeng , Zhichao Feng and et al.," Combination network (DCN): towards accurate diagnosis and lesion segmentation of COVID-19 using CT images", Medical Image Analysis (2020), doi: https://doi.org/10.1016/j.media.2020.101836.
  30. Edelson Damasceno Carvalho, Edson Damasceno Carvalho, and Antonio Oseas de Carvalho Filho ," COVID-19 diagnosis in CT images using CNN to extract features and multiple classifiers", 2020 IEEE 20th International Conference on BioInformatics and BioEngineering (BIBE). DOI 10.1109/BIBE50027.2020.00075S.N.