AN INTELLIGENT DETECTION SYSTEM FOR COVID-19 DIAGNOSIS USING CT-IMAGES

Hasan, Amira; Abd El Kader, Hala; Hossam, Aya

doi:10.21608/jesaun.2021.61028.1031

AN INTELLIGENT DETECTION SYSTEM FOR COVID-19 DIAGNOSIS USING CT-IMAGES

Document Type : Research Paper

Authors

¹ Engineer, Electrical Engineering Department Alexandria Higher Institute of Engineering Technology (AIET),Alex, Egypt

² Professor, Electrical Engineering, Department, Faculty of Engineering (Shoubra), Benha University, Cairo, Egypt

³ Lecturer, Electrical Engineering, Department, Faculty of Engineering (Shoubra), Benha University, Cairo, Egypt

10.21608/jesaun.2021.61028.1031

Abstract

Early classification of the Coronavirus disease (COVID-19) is necessary to control its rapid spread and save patients’ lives. The fast spread of COVID-19 has increased the diagnostic encumbrance of radiologists. Therefore, clinicians need to quickly assess if a patient has COVID-19 or not. Artificial Intelligence (AI) has shown promising results in healthcare. So, this paper proposed a computer-aided intelligence model that can identify positive COVID-19 cases. It presented the pipeline of medicinal imaging and examination methods involved in COVID-19 image acquirement, segmentation, and diagnosis, using Computed Tomography (CT) images. This paper introduced two effective models for single machine learning (SML) and ensemble machine learning (EML) with 10-fold cross validation, to detect cases of COVID-19.The first classification model (SML) was applied with different algorithms, such as Decision Tree (DT), Artificial Neural Networks (ANN), and Support Vector Machines (SVM). Results showed that the performance of the SVM surpassed other classifiers with a 98.85 % accuracy. The second classification model (EML) was applied with several algorithms, such as Random Forest (RF), Voting, and Bagging, to increase its accuracy up to 99.60%, especially using the Bagging classifier. Finally, the results of the two proposed models showed better performance compared with other recent studies. However, the EML showed an even better performance than SML and is recommended for use in real-time.

Keywords

Main Subjects

Electrical Engineering, Computer Engineering and Electrical power and machines engineering.

References

[1] C. Huang, Y. Wang, X. Li, L. Ren, J. Zhao, Y. Hu, & B. Cao, Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. The lancet, vol.395, no.10223, pp. 497-506, 2020.

[2] N. Chen, M. Zhou, X. Dong, J. Qu, F. Gong, Y. Han & L. Zhang, Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. The lancet, vol.395, no.10223, pp.507-513, 2020.

[3] D. S. Hui, E. I. Azhar, T. A. Madani, F. Ntoumi, R. Kock, O. Dar, & E. Petersen, the continuing 2019-nCoV epidemic threat of novel coronaviruses to global health—the latest 2019 novel coronavirus outbreak in Wuhan, China. International journal of infectious diseases, vol.91, no. 264-266, 2020.

[4] J. F. W. Chan, K. K. W. To, H. Tse, D. Y. Jin, & K. Y. Yuen, Interspecies transmission, and emergence of novel viruses: lessons from bats and birds. Trends in microbiology, vol. 21, no.10, pp. 544-555, 2013.

[5] World Meters: Covid-19 Coronavirus Pandemic; Accessed on: January 2021, https://www.worldometers.Info/Coronavirus/

[6] World Health Organization; Coronavirus disease (COVID-19) advice for the public. Accessed on: April 11, 2020, https://www.who.int/emergencies/diseases/novel-coronavirus-2019/advice-for-public.

[7] A. Narin, C. Kaya & Z. Pamuk. Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks. ArXiv preprint ArXiv: 2003.10849.‏

[8] A. Hossam, A. Magdy, A. Fawzy & S. M. Abd El-Kader. An integrated IOT system to control the spread of COVID-19 in Egypt. In International Conference on Advanced Intelligent Systems and Informatics, Springer, Cham, pp. 336-346, 2020.

[9] A. Hossam & A. Fawzy, A rapid diagnosis tool based on LASER for fighting COVID-19. International Journal of Microwave and Optical Technology, vol.15, no, 5, 2020.

[10] K. Li, Y. Fang, W. Li, C. Pan, P. Qin, Y. Zhong, X. Liu, M. Huang, Y. Liao, and S. Li, 2020. CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19). European radiology, vol. 30, no. 8, pp.4407-4416, 2020.

[11] J. Bullock, A. Luccioni, K. H. Pham, C. S. N. Lam, & M. Luengo-Oroz, Mapping the landscape of artificial intelligence applications against COVID-19. Journal of Artificial Intelligence Research, vol. 69, no. 807-845, 2020.

[12] L. Wang, Z. Q. Lin, & A. Wong. Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, vol. 10, no.1, pp. 1-12, 2020.

[13] L. Yan, H. T. Zhang, Y. Xiao, M. Wang, Y. Guo, C. Sun & Y. Yuan, Prediction of criticality in patients with severe Covid-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan, 2020.

[14] S. El-bana, A. Al-Kabbany & M. Sharkas. A multi-task pipeline with specialized streams for classification and segmentation of infection manifestations in covid-19 scans. PeerJ Computer Science, vol.6, e303, 2020.

[15] J. Wang, J. Wu, J., Z. Wu, J. Jeong, & G. Jeon. Wiener filter-based wavelet domain denoising. Displays, 46, 37-41, 2017.

[16] P. Garg & T. Jain. A comparative study on histogram equalization and cumulative histogram equalization. International Journal of New Technology and Research, vol.3, no.9, pp. 263242, 2017.‏

[17] X. Chen, L. Yao, & Y. Zhang, Residual attention u-net for automated multi-class segmentation of covid-19 chest CT images. ArXiv preprint ArXiv: 2004.05645, 2020.

[18] A. E. Hassanien, L. N. Mahdy, K. A. Ezzat, H. H. Elmousalami, & H. A. Ella, Automatic x-ray covid-19 lung image classification system based on multi-level Thresholding and support vector machine. MedRxiv, 2020.

[19] J. H. Uhl, S. Leyk, Y. Y. Chiang, W. Duan & C. A. Knob lock. Spatializing uncertainty in image segmentation using weakly supervised convolutional neural networks: a case study from historical map processing. IET Image Processing, vol.12, no. 11, pp. 2084-2091, 2018.

[20] F. Shan, Y. Gao, J. Wang, W. Shi, N. Shi, M. Han & Y. Shi. Lung infection quantification of COVID-19 in CT images with deep learning. ArXiv preprint ArXiv: 2003.04655,2020.

[21] D. P. Fan, T. Zhou, G. P. Ji, Y. Zhou, G. Chen, H. Fu & L. Shao. Inf-net: Automatic covid-19 lung infection segmentation from CT images. IEEE Transactions on Medical Imaging, vol.39, no.8, pp. 2626-2637, 2020.

[22] J. Ma, Z. Nie, C. Wang, G. Dong, Q. Zhu, J. He & X. Yang. Active contour regularized semi-supervised learning for COVID-19 CT infection segmentation with limited annotations. Physics in Medicine & Biology, vol.65, no.22, pp. 225034, 2020.

[23] T. Bhatia. An image-processing method to detect sub-optical features based on understanding noise in intensity measurements. European Biophysics Journal, vol. 47, no. 5, pp. 531-538, 2018.

[24] S. Varela-Santos, & P. Melin. A new approach for classifying coronavirus COVID-19 based on its manifestation on chest X-rays using texture features and neural networks. Information sciences, vol.545, pp. 403-414, 2021.

[25] H. Zhang, C. L. Hung, G. Min, J. P. Guo, M. Liu & X. Hu, GPU-accelerated GLRLM algorithm for feature extraction of MRI. Scientific reports, vol. 9, no.1, pp.1-13,2019

[26] P. K. Chandrakar, A. K. Shrivas, & N. Sahu, Design of a Novel Ensemble Model of Classification Technique for Gene-Expression Data of Lung Cancer with Modified Genetic Algorithm. EAI Endorsed Transactions on Pervasive Health and Technology, vol. 7, no.25, pp. e2, 2021.

[27] M. Zivkovic, N. Bacanin, K. Venkatachalam, A. Nayyar, A. Djordjevic, I. Strumberger & F. Al-Turjman, COVID-19 cases prediction by using hybrid machine learning and beetle antennae search approach. Sustainable Cities and Society, vol.66, pp.102669, 2021.

[28] M. Zaman & A. Hassan, Fuzzy Heuristics and Decision Tree for Classification of Statistical Feature-Based Control Chart Patterns. Symmetry, vol.13, no.1, pp.110, 2021.

[29] A. M. Ali, K. Z. Ghafoor, H. S. Maghdid, & A. Mulahuwaish. Diagnosing COVID-19 Lung Inflammation Using Machine Learning Algorithms: A Comparative Study. In Internet of Medical Things for Smart Healthcare, pp. 91-105, Springer, Singapore, 2020.

[30] M. Ilyas, H. Rehman & A. Naït-Ali. Detection of covid-19 from chest x-ray images using artificial intelligence: An early review. ArXiv preprint ArXiv: 2004.05436, 2020.

[31] A. R. M. T. Islam, S. Talukdar, S. Mahato, S. Kundu, K. U. Eibek, Q. B. Pham, & N. T. T. Linh. Flood susceptibility modelling using advanced ensemble machine learning models. Geoscience Frontiers, vol.12, no.3, pp. 101075, 2021.

[32] R. Mostafiz, M. S. Uddin, N. A. Alam, M.M. Reza, & M. M. Rahman, M. Covid-19 Detection in Chest X-ray through Random Forest Classifier using a Hybridization of Deep CNN and DWT Optimized Features. Journal of King Saud University-Computer and Information Sciences, 2020.

[33] T. Bahadur Chandra, K. Verma, B. Kumar Singh, D. Jain, & S. Singh Netam, Coronavirus Disease (COVID-19) Detection in Chest X-Ray Images using Majority Voting Based Classifier Ensemble. Expert Syst Appl, 113909-113909, 2020.

[34] A. Wadhawan, Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting. ArXiv preprint ArXiv: 2010.00294, ‏2020.

[35] :https://www.kaggle.com/luisblanche/covidct?select=CT_NonCOVID

[36] GitHub - UCSD-AI4H/COVID-CT: COVID-CT-Dataset: A CT Scan Dataset about COVID-19

[37] S. Kadry, V. Rajinikanth, S. Rho, N. S. M. Raja, V.S. Rao & K. P. Thanaraj, Development of a machine-learning system to classify lung CT scan images into normal/covid-19 class. ArXiv preprint ArXiv: 2004.13122, 2020.

[38] A. Hossam, H. M. Harb, & H. M. Abd El Kader. Automatic image segmentation method for breast cancer analysis using thermography. JES. Journal of Engineering Sciences, vol.46, no.1, pp.12-32, 2018.

[39] Z. Fang, Z. Xu, T. Jang, F. Zhou & S. Huang, Standard deviation Quantitative Characterization and Process Optimization of the Pyramidal Texture of Mon crystalline Silicon Cells. Materials, vol.13, no.3, pp.564, 2020.