COVID-19 Detection from Chest X-rays Using Pre-Trained Models and Compact Convolutional Transformers with Grad-CAM Visualization
COVID-19 Detection from Chest X-rays Using Pre-Trained Models and Compact Convolutional Transformers with Grad-CAM Visualization |
||
![]() |
![]() |
|
© 2025 by IJETT Journal | ||
Volume-73 Issue-7 |
||
Year of Publication : 2025 | ||
Author : Revathi A, Balaji Savadam | ||
DOI : 10.14445/22315381/IJETT-V73I7P127 |
How to Cite?
Revathi A, Balaji Savadam, "COVID-19 Detection from Chest X-rays Using Pre-Trained Models and Compact Convolutional Transformers with Grad-CAM Visualization," International Journal of Engineering Trends and Technology, vol. 73, no. 7, pp.339-356, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I7P127
Abstract
For the early and accurate detection of COVID-19, which is necessary for timely diagnosis and treatment, Chest X-Ray (CXR) imaging is crucial. Developing automated and reliable detection techniques is crucial because traditional diagnostic techniques, such as real-time Reverse Transcription-Polymerase Chain Reaction (RT-PCR), are time-consuming and prone to false negative results. This paper presents a compact and efficient Deep Learning (DL) system that uses pre-trained models and compact convolutional transformers to enhance feature extraction. The proposed model, TCovNet, uses an EfficientNet-B4 backbone and Gradient-weighted Class Activation Mapping (Grad-CAM) to generate comprehensible visual explanations for observed abnormalities. Additionally, contrast-limited adaptive histogram equalization CLAHE improves image clarity and model performance. The method was tested using balanced and imbalanced data distributions using publicly accessible COVID-19 CXR datasets. Experimental results demonstrate that TCovNet outperforms the current state-of-the-art techniques, with a classification accuracy of 98.5%. The use of Grad-CAM improves transparency and interpretability, making the model appropriate for clinical decision assistance. This study emphasizes the productivity of transformer-based architectures in medical imaging, besides the implication of explainability in DL-based COVID-19 diagnostic tools.
Keywords
Grad-CAM, X-ray, Convolutional Neural Networks (CNN), CLAHE, Edge computing, Deep Learning, Visualization.
References
[1] Isabel Bergeri et al., “Early Epidemiological Investigations: World Health Organization UNITY Protocols Provide a Standardized and Timely International Investigation Framework during the COVID‐19 Pandemic,” Influenza and Other Respiratory Viruses, vol. 16, no. 1, pp. 7-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Awad A. Shehata et al., “Diversity of Coronaviruses with Particular Attention to the Interspecies Transmission of SARS-CoV-2,” Animals, vol. 12, no. 3, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ke Men et al., “Estimate the Incubation Period of Coronavirus 2019 (COVID-19),” Computers in Biology and Medicine, vol. 158, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Anacleto Silva de Souza et al., “Severe Acute Respiratory Syndrome Coronavirus 2 Variants of Concern: A Perspective for Emerging More Transmissible and Vaccine-Resistant Strains,” Viruses, vol. 14, no. 4, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Prafull Kamble et al., “Synopsis of Symptoms of COVID-19 during the Second Wave of the Pandemic in India,” Hormone Molecular Biology and Clinical Investigation, vol. 43, no. 1, pp. 97-104, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Alana Teles Costa et al., “Policy Responses from Countries with the Highest Number of COVID-19 Deaths in the World: A Scoping Review,” Research, Society and Development, vol. 11, no. 12, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Pei-Chin Lin et al., “Diagnostic Performance of GenBody COVID-19 Rapid Antigen Test for Laboratory and Non-Laboratory Medical Professionals in Real Practice: A Retrospective Study,” Medicine, vol. 102, no. 33, pp. 1-5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Inayatullah Shah Sayed, and Nor Fitri Toh Man Hua, “Role of X-Ray CT, Plain Radiography and Ultrasound Imaging in Diagnosing COVID-19: A Narrative Review,” International Journal of Allied Health Sciences, vol. 7, no. 2, pp. 2933-2944, 2023.
[Google Scholar] [Publisher Link]
[9] Shahanaz Abdul Gafoor et al., “Deep Learning Model for Detection of COVID-19 Utilizing the Chest X-Ray Images,” Cogent Engineering, vol. 9, no. 1, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Claudia Ravaglia et al., “Clinical, Radiological and Pathological Findings in Patients with Persistent Lung Disease Following SARS-CoV-2 Infection,” European Respiratory Journal, vol. 60, no. 4, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Sajid Iqbal et al., COVID-19 Prediction, Diagnosis and Prevention through Computer Vision, Prognostic Models in Healthcare: AI and Statistical Approaches, Springer, Singapore, pp. 79-113, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Kirti Raj Bhatele et al., “COVID-19 Detection: A Systematic Review of Machine and Deep Learning-Based Approaches Utilizing Chest X-Rays and CT Scans,” Cognitive Computation, vol. 16, no. 4, pp. 1889-1926, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Luca Brunese et al., “Explainable Deep Learning for Pulmonary Disease and Coronavirus COVID-19 Detection from X-Rays,” Computer Methods and Programs in Biomedicine, vol. 196, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Mamta Patel, and Mehul Shah, “Transfer Learning with Fine-Tuned Deep CNN Model for COVID-19 Diagnosis from Chest X-ray Images,” International Journal of Advanced Technology and Engineering Exploration, vol. 10, no. 103, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Saeed Iqbal et al., “Dynamic Learning for Imbalanced Data in Learning Chest X-Ray and CT Images,” Heliyon, vol. 9, no. 6, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Morsheda Akter et al., “Human Activity Recognition using Attention-Mechanism-based Deep Learning Feature Combination,” Sensors, vol. 23, no. 12, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Farhad Maleki et al., “Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls,” Radiology: Artificial Intelligence, vol. 5, no. 1, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Chiagoziem C. Ukwuoma et al., “Multi-Classification of Breast Cancer Lesions in Histopathological Images using DEEP_Pachi: Multiple Self-Attention Head,” Diagnostics, vol. 12, no. 5, pp. 1-32, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Chiagoziem C. Ukwuoma et al., “Deep Learning Framework for Rapid and Accurate Respiratory COVID-19 Prediction using Chest X-ray Images,” Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 7, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Soumya Ranjan Nayak et al., “An Automated Lightweight Deep Neural Network for Diagnosis of COVID-19 from Chest X-ray Images,” Arabian Journal for Science and Engineering, vol. 48, no. 8, pp. 11085-11102, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Essam H Houssein et al., “Hybrid Quantum-Classical Convolutional Neural Network Model for COVID-19 Prediction using Chest X-ray Images,” Journal of Computational Design and Engineering, vol. 9, no. 2, pp. 343-363, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Anika Tahsin Meem et al., “Prediction of COVID-19 based on Chest X-ray Images using Deep Learning with CNN,” Computer Systems Science and Engineering, vol. 41, no. 3, pp. 1223-1240, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Chiagoziem C. Ukwuoma et al., “Automated Lung-Related Pneumonia and COVID-19 Detection based on Novel Feature Extraction Framework and Vision Transformer Approaches using Chest X-ray Images,” Bioengineering, vol. 9, no. 11, pp. 1-27, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Mohamad Mahmoud Al Rahhal et al., “Contrasting EfficientNet, ViT, and gMLP for COVID-19 Detection in Ultrasound Imagery,” Journal of Personalized Medicine, vol. 12, no. 10, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Saleh Albahli, and Ghulam Nabi Ahmad Hassan Yar, “Efficient Grad-Cam-Based Model for COVID-19 Classification and Detection,” Computer Systems Science and Engineering, vol. 44, no. 3, pp. 2743-2757, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[26] K. Srinivas et al., “COVID-19 Prediction based on Hybrid Inception V3 with VGG16 using Chest X-ray Images,” Multimedia Tools and Applications, vol. 83, no. 12, pp. 36665-36682, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Muhammad Umer et al., “COVINet: A Convolutional Neural Network Approach for Predicting COVID-19 from Chest X-Ray Images,” Journal of Ambient Intelligence and Humanized Computing, vol. 13, no. 1, pp. 535-547, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Md. Nahiduzzaman, Md. Rabiul Islam, and Rakibul Hassan, “ChestX-Ray6: Prediction of Multiple Diseases Including COVID-19 from Chest X-ray Images using Convolutional Neural Network,” Expert Systems with Applications, vol. 211, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Mohit Kumar et al., “COVID-19 Prediction through X-Ray Images using Transfer Learning-based Hybrid Deep Learning Approach,” Materials Today: Proceedings, vol. 51, pp. 2520-2524, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] A. Arivoli, Devdatt Golwala, and Rayirth Reddy, “CoviExpert: COVID-19 Detection from Chest X-Ray using CNN,” Measurement: Sensors, vol. 23, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Karen Simonyan, and Andrew Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” 3rd International Conference for Learning Representations, San Diego, CA, USA, pp. 1-14, 2015.
[Google Scholar] [Publisher Link]
[33] François Chollet, “Xception: Deep Learning with Depth-Wise Separable Convolutions,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 1800-1807, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Saleh Albahli, Nasir Ayub, and Muhammad Shiraz, “Coronavirus Disease (COVID-19) Detection using X-ray Images and Enhanced DenseNet,” Applied Soft Computing, vol. 110, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Tawsifur Rahman, Muhammad Chowdhury, and Amith Khandakar, COVID-19 Radiography Database, Kaggle, 2020. [Online]. Available: https://www.kaggle.com/tawsifurrahman/COVID19-radiography-database
[36] Amal H. Alharbi et al., “Detection of Peripheral Malarial Parasites in Blood Smears using Deep Learning Models,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Xuebin Yue et al., “Machine Learning-based Apathy Classification on Doppler Radar Image for the Elderly Person,” Procedia Computer Science, vol. 187, pp. 146-151, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Naoto Nojiri et al., “Apathy Classification based on Doppler Radar Image for the Elderly Person,” Frontiers in Bioengineering and Biotechnology, vol. 8, pp. 1-16, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Lin Meng et al., “Oracle Bone Inscription Detector based on SSD,” International Conference on Image Analysis and Processing, Trento, Italy, pp. 126-136, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Asmaa Abbas, Mohammed M. Abdelsamea, and Mohamed Medhat Gaber, “Classification of COVID-19 in Chest X-Ray Images using DeTraC Deep Convolutional Neural Network,” Applied Intelligence, vol. 51, no. 2, pp. 854-864, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Ramprasaath R. Selvarajuet al., “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” International Journal of Computer Vision, vol. 128, no. 2, pp. 336-359, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Mingxing Tan, and Quoc Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, vol. 97, pp. 6105-6114, 2019.
[Google Scholar] [Publisher Link]
[43] Chia-Wei Jan et al., “Optical based Gradient-Weighted Class Activation Mapping and Transfer Learning Integrated Pneumonia Prediction Model,” Computer Systems Science and Engineering, vol. 47, no. 3, pp. 2989-3010, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Ying Song et al., “Deep Learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT Images,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18, no. 6, pp. 2775-2780, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[45] Mohamed Loey, Florentin Smarandache, and Nour Eldeen M. Khalifa, “Within the Lack of Chest COVID-19 X-Ray Dataset: A Novel Detection Model based on GAN and Deep Transfer Learning,” Symmetry, vol. 12, no. 4, pp. 1-19, 2020.
[CrossRef] [Google Scholar] [Publisher Link]