Classification of COVID-19 from Chest CT Images Using Ensemble Techniques
10.14416/j.ind.tech.2025.08.004
Keywords:
Classification of COVID-19, Chest CT scan, Ensemble Techniques, Deep LearningAbstract
The COVID-19 pandemic has emphasized the critical need for effective diagnostic tools that can assist medical personnel in evaluating patients more rapidly and accurately. This research presents the development of a model for classifying COVID-19 from chest computed tomography (CT) scans using ensemble learning methods. The study utilized the COVID-19 Radiography dataset containing 7,232 images, evenly divided between 3,616 COVID-19 positive images and 3,616 COVID-19 negative images. The dataset was split data to a training set (70%, 2,531 images), validation set (20%, 723 images), and test set (10%, 362 images), with 5-fold cross-validation (K=5). The experimental methodology was divided into three groups: Group 1 involved testing 38 popular deep learning models and selecting the three highest-accuracy models for further experimentation. Group 2 combined these models using bagging techniques across the five cross-validation data folds in three different experimental configurations. Group 3 utilized bagging to combine the highest-performing versions of each selected model in two experimental configurations. The results show that the experiment group 3 using MobileNet and DenseNet121 together achieved an accuracy of 99.30%, compared to the baseline model in group 1 with an accuracy of 97.23%, which is 2.07% higher.
References
M.M. Hossain, Md.A.A. Walid, S.M.S. Galib, M.M. Azad, W. Rahman, AS.M. Shafi and M.M. Rahman, COVID-19 detection from chest CT images using optimized deep features and ensemble classification, Systems and Soft Computing, 2024, 6, 200077.
M.A. Ganaie, M. Hu, A.K. Malik, K. Tanveer and P.N. Suganthan, Ensemble deep learning: A review, Engineering Applications of Artificial Intelligence, 2022, 115, 105-151.
H.-C. Kim, S. Pang, H.-M. Je, D. Kim and S.-Y. Bang, Support vector machine ensemble with bagging, Pattern Recognition with Support Vector Machines, 2002, 397-408.
M. LesBlanc and R. Tibshirani, Combining estimates in regression and classification, Journal of the American Statistical Association, 1996, 91(436), 1641-1650.
L. Breiman, Bagging predictors, Machine learning, 1997, 24, 123-140.
S. Chaurasia, A.K. Gupta, P.P. Tiwari, A. Smirti and M. Jangid, DSENetk: An efficient deep stacking ensemble approach for COVID-19 induced pneumonia prediction using radiograph images, SN Computer Science, 2025, 6, 68.
G.N. Chandrika, R. Chowdhury, P. Kumar, K. Sangamithrai, E. Glory and M.D. Saranya, Ensemble learning based convolutional neural network – depth fire for detecting COVID-19 in chest X-Ray images, Journal of Electronics Electromedical Engineering, and Medical Informatics, 2024, 7(1), 47-55.
T. Geroski, V. Rankovic, O. Pavic, L. Dasic, M. Petrovic, D. Milovanovic and N. Filipovic, Enhancing COVID-19 disease severity classification through advanced transfer learning techniques and optimal weight initialization schemes, Biomedical Signal Processing and Control, 2025, 100, Part C, 107103.
S. Kumar and H. Kumar, Efficient-VGG16: A novel ensemble method for the classification of COVID-19 X-ray images in contrast to machine and transfer learning, Procedia Computer Science, 2024, 235, 1289-1299.
S. Asif, M. Zhao, F. Tang and Y. Zhu, LWSE: a lightweight stacked ensemble model for accurate detection of multiple chest infectious diseases including COVID-19, Multimedia Tools and Applications, 2024, 83(8), 23967-24003.
S. Wang, J. Ren and X. Guo, A high-accuracy lightweight network model for X-ray image diagnosis: A case study of COVID detection, PLoS ONE, 2024, 19(6), e0303049.
https://www.kaggle.com/datasets/tawsifurr-ahman/covid19-radiography-database/. (Accessed on 10 January 2025)
P. Chedsom and W. Kanarkard, Analysis of student engagement in online classroom using convolutional neural networks (CNN), ECTI Transaction on Application Research and Development, 2023, 3(3), 39-52. (in Thai)
D.P. Kingma and J. Ba, Adam: A method for stochastic optimization, The 3rd International Conference for Learning Representations, Proceeding, 2015.
A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand M. Andreetto and H. Adam, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv, 2017, 1704.04861.
G. Huang, Z. Liu, L. Maaten and Q. Weinberger, Densely connected convolutional networks, IEEE conference on computer vision and pattern recognition, Proceedings, 2017, 4700-4708.
