A Novel Multi-Head Attention Framework for COVID-19 Detection: Hybrid Integration of MobileNet and VGG19 with Enhanced Feature Learning

Öz

The COVID-19 pandemic has underscored the urgent need for rapid, accurate, and affordable diagnostic tools to complement RT-PCR testing. This study proposes a novel multi-head attention framework that integrates VGG19 and MobileNet for automated COVID-19 detection from chest X-rays. The model employs a hybrid mechanism combining spatial, channel, and self-attention components, enhancing feature representation while preserving efficiency. Evaluations on 7,132 chest X-ray images across four categories (COVID-19, Normal, Pneumonia, Tuberculosis) demonstrated outstanding performance: 99.0% accuracy, 99.0% macro and weighted F1-scores, with near-perfect class-specific results (100% Tuberculosis, 99.7% COVID-19, 99.5% Normal, 96.0% Pneumonia). Inference time was only 63 ms per image, with a compact 14.8 MB model size. These results surpass baseline MobileNet and DenseNet121 by 2.63% and 4.32%, respectively. The proposed framework offers reliable rapid screening and differential diagnosis, supported by interpretable attention maps, making it highly suitable for deployment in resource-limited healthcare and point-of-care settings.

Anahtar Kelimeler

• COVID-19 Detection
• Deep Learning
• Multi-Head Attention Mechanism
• Medical Image Analysis
• VGG19

COVID-19 Tespiti için Yeni Bir Çok Başlı Dikkat Çerçevesi: MobileNet ve VGG19 Tabanlı Geliştirilmiş Özellik Öğrenimi ile Hibrit Entegrasyon

Öz

COVID-19 pandemisi, RT-PCR testlerini destekleyecek hızlı, doğru ve maliyet etkin tanı araçlarına duyulan ihtiyacı ortaya koymuştur. Bu çalışmada, göğüs röntgeni görüntülerinden otomatik COVID-19 tespiti için VGG19 ve MobileNet mimarilerini entegre eden yeni bir çok başlı dikkat çerçevesi önerilmektedir. Model, uzamsal, kanal ve çok başlı öz-dikkat mekanizmalarını birleştirerek özellik çıkarımını güçlendirirken hesaplama verimliliğini korumaktadır. Yaklaşımımız 7.132 görüntüden oluşan dört sınıflı veri kümesinde test edilmiştir (COVID-19, Normal, Pnömoni, Tüberküloz). Dikkat mekanizmasıyla geliştirilmiş MobileNet %99,0 doğruluk, makro ve ağırlıklı F1 skorları elde etmiştir. Sınıf bazında %100 Tüberküloz, %99,7 COVID-19, %99,5 Normal ve %96,0 Pnömoni doğruluğu kaydedilmiştir. Ayrıca model, 14,8 MB boyutu ve 63 ms çıkarım süresi ile klinik uygulanabilirliğe sahiptir. Sonuçlar, mevcut yöntemlere göre %2,63–%4,32 iyileşme göstermekte olup, modelin güvenilir hızlı tarama ve ayırıcı tanıda etkili olduğunu göstermektedir.

Anahtar Kelimeler

• COVID-19 Tespiti
• Derin Öğrenme
• Çok Başlı Dikkat Mekanizması
• Tıbbi Görüntü İşleme
• VGG19

Kaynakça

1. 1. World Health Organization (2024). Coronavirus disease (Covid-19). https://www.who.int/health-topics/coronavirus, Erişim tarihi: 18 Kasım 2024.
2. 2. Wang, L., Lin, Z. Q. & Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Sci Rep. 10, 19549
3. 3. Li, C., Dong, D., Li, L., Gong, W., Li, X., Bai, Y., Wang, M., Hu, Z., Zha, Y. & Tian, J. (2020). Classification of severe and critical covid-19 using deep learning and radiomics. IEEE Journal of Biomedical and Health Informatics, 24(12), 3585-3594.
4. 4. Roberts, M., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Aviles-Rivero, A. I., Etmann, C., McCague, C., Beer, L., Weir-McCall, J., Teng, Z., Gkrania-Klotsas, E., Rudd, J.H., Sala, E., Schönlied, C.-B. & Gozaliasi, G. (2021). Common pitfalls and recommendations for using machine learning to detect and prognosticate for covid-19 using chest radiographs and ct scans. Nature Machine Intelligence, 3(3), 199-217.
5. 5. Khan, S.H., Sohail, A., Khan, A., Hassan, M., Lee, Y.S., Alam, J., Basit, A. & Zubair, S. (2021). Covid-19 detection in chest x-ray images using deep boosted hybrid learning. Computers in Biology and Medicine, 137, 104816.
6. 6. Hryniewska, W., Bombinski, P., Szatkowski, P., Tomaszewska, P., Przelaskowski, A. & Biecek, P. (2021). Checklist for responsible deep learning modeling of medical images based on covid-19 detection studies. Pattern Recognition, 118, 108035.
7. 7. Schlemper, J., Oktay, O., Schaap, M., Heinrich, M., Kainz, B., Glocker, B. & Rueckert, D. (2019). Attention gated networks: Learning to leverage salient regions in medical images. Medical Image Analysis, 53, 197-207.
8. 8. Zhou, S.K., Greenspan, H., Davatzikos, C., Duncan, J.S., Van Ginneken, B., Madabhushi, A., Prince, J.L., Rueckert, D. & Summers, R.M. (2021). A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises. Proceedings of the IEEE, 109(5), 820-838.

9. 9. Wang, L., Lin, Z. Q. & Wong, A. (2021). Covid-net: a tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, 11(1), 1-12.
10. 10. Kılıç, Ş. (2025). Attention-based dual-path deep learning for blood cell image classification using ConvNeXt and swin transformer. Journal of Imaging Informatics in Medicine, 1-19.
11. 11. Özüpak, Y. (2024). Evrişimli sinir ağı (ESA) mimarileri ile hücre görüntülerinden sıtmanın tespit edilmesi, Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(1), 197-210.
12. 12. Han, Z., Wei, B., Hong, Y., Li, T., Cong, J., Zhu, X., Wei, H. & Zhang, W. (2020). Accurate screening of covid-19 using attention-based deep 3d multiple instance learning. IEEE Transactions on Medical Imaging, 39(8), 2584-2594.
13. 13. Karthik, R., Menaka, R., Hariharan, M. & Won, D. (2022). Contour-enhanced attention cnn for ct-based covid-19 segmentation. Pattern Recognition, 125, 108538.
14. 14. Zhang, Y., Niu, S., Qiu, Z., Wei, Y., Zhao, P., Yao, J., Huang, J., Wu, Q. & Tan, M. (2020). Covid-da: Deep domain adaptation from typical pneumonia to covid-19. arXiv preprint, arXiv:2005.01577.
15. 15. Xu, X., Jiang, X., Ma, C., Du, P., Li, X., Lv, S., Yu, L., Ni, Q., Chen, Y., Su, J., Lang, G., Li, Y., Zhao, H., Liu, J., Xu, K., Ruan, L., Sheng, J., Qiu, Y., Wu, W., Liang T. & Li, L. (2020). A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering, 6(10), 1122-1129.
16. 16. Park, J., Yu, Y., Han, T., Cho, H., Choi, S., Lee, Y., Park, S. & Yoo, J. (2022). Vision transformer using low-level chest x-ray feature corpus for covid-19 diagnosis and severity quantification. Medical Image Analysis, 75, 102299.
17. 17. Singh, D., Kumar, V. & Kaur, M. (2021). Densely connected convolutional networks-based covid-19 screening model, Applied Intelligence, 51, 3044-3051.
18. 18. Zhou, S. & Qiu, J. (2021). Enhanced ssd with interactive multi-scale attention features for object detection. Multimedia Tools and Applications, 80, 11539-11556.
19. 19. Akter, S., Shamrat, F. J. M., Chakraborty, S., Karim, A. & Azam, S. (2021). Covid-19 detection using deep learning algorithm on chest x-ray images. Biology, 10(11), 1174.
20. 20. Liu, G. & Guo, J. (2019). Bidirectional lstm with attention mechanism and convolutional layer for text classification. Neurocomputing, 337, 325-338.
21. 21. Wang, Q., Han, T., Qin, Z., Gao, J. & Li, X. (2020). Multitask attention network for lane detection and fitting, IEEE Transactions on Neural Networks and Learning Systems, 33(3), 1066-1078.
22. 22. Kılıç, Ş. (2025). HybridVisionNet: An advanced hybrid deep learning framework for automated multi-class ocular disease diagnosis using fundus imaging. Ain Shams Engineering Journal, 16(10), 103594.
23. 23. Lin, Z., He, Z., Xie, S., Wang, X., Tan, J., Lu, J. & Tan, B. (2021). AANet: Adaptive attention network for COVID-19 detection from chest X-ray images. IEEE Transactions on Neural Networks and Learning Systems, 32(11), 4781-4792.
24. 24. Saddique, A., Manan, A., Ali, M., Siddiqui, S. & Rehan, M. (2025). Hybrid deep learning models for multi-class classification of chest X-ray images: Normal, pneumonia, and COVID-19. Spectrum of Engineering Sciences, 3(7), 21-33.
25. 25. Wang, X., Wang, S., Zhang, Z., Yin, X., Wang, T. & Li, N. (2023). Cpad-net: Contextual parallel attention and dilated network for liver tumor segmentation. Biomedical Signal Processing and Control, 79, 104258.
26. 26. Ghosh, S. & Chatterjee, A. (2023). Automated COVID-19 CT image classification using multi-head channel attention in deep CNN. arXiv preprint, arXiv:2308.00715.
27. 27. Zhou, T., Chang, X., Liu, Y., Ye, X., Lu, H. & Hu, F. (2023). COVID-ResNet: COVID-19 recognition based on improved attention ResNet. Electronics, 12(6), 1413.
28. 28. Ibrahim, W.R. & Mahmood, M.R. (2023). Classified covid-19 by densenet121-based deep transfer learning from ct-scan images. Science Journal of University of Zakho, 11(4), 571-580.
29. 29. Canayaz, M. (2021). C+EffxNet: A novel hybrid approach for COVID-19 diagnosis on CT images based on CBAM and EfficientNet. Chaos, Solitons & Fractals, 151, 111310.
30. 30. Yang, H., Wang, L., Xu, Y. & Liu, X. (2023). CovidViT: A novel neural network with self-attention mechanism to detect COVID-19 through X-ray images. International Journal of Machine Learning and Cybernetics, 14(3), 973-987.
31. 31. Erdem, E. & Aydin, T. (2021). Deep hybrid models for CT images to detect COVID-19: A comparison of transfer learning approach. Journal of Soft Computing and Artificial Intelligence, 2(2), 56-68.
32. 32. Lin, Z., He, Z., Yao, R., Wang, X., Liu, T., Deng, Y. & Xie, S. (2022). Deep dual attention network for precise diagnosis of COVID-19 from chest CT images. IEEE Transactions on Artificial Intelligence, 5(1), 104-114.
33. 33. Yang, L., Hu, T., Zhang, X., Chen, X., Wu, A. & Chang, J. (2023). Enhanced classification of COVID-19 CT images using CDenseNet with CBAM attention and Swish activation. 2023 5th International Conference on Artificial Intelligence and Computer Applications (ICAICA), 160-165. IEEE.
34. 34. Li, J., Wang, Y., Wang, S., Wang, J., Liu, J., Jin, Q. & Sun, L. (2021). Multiscale attention guided network for COVID-19 diagnosis using chest X-ray images. IEEE Journal of Biomedical and Health Informatics, 25(5), 1336-1346.
35. 35. Tan, Z., Yu, Y., Meng, J., Liu, S. & Li, W. (2024). Self-supervised learning with self-distillation on COVID-19 medical image classification. Computer Methods and Programs in Biomedicine, 243, 107876.
36. 36. Yang, Y., Zhang, L., Ren, L. & Wang, X. (2023). MMViT-Seg: A lightweight transformer and CNN fusion network for COVID-19 segmentation. Computer Methods and Programs in Biomedicine, 230, 107348.
37. 37. Sun, Y., Lian, J., Teng, Z., Wei, Z., Tang, Y., Yang, L., Zhou, J., Xu, K., Zhang, W., Liu, H., Chen, R. & Lei, B. (2024). COVID-19 diagnosis based on swin transformer model with demographic information fusion and enhanced multi-head attention mechanism. Expert Systems with Applications, 243, 122805.
38. 38. Tian, G., Wang, Z., Wang, C., Chen, J., Liu, G., Xu, H., Li, Y., Zhang, Q., Huang, X., Zhou, M. & Peng, L. (2022). A deep ensemble learning-based automated detection of COVID-19 using lung CT images and vision transformer and ConvNeXt. Frontiers in Microbiology, 13, 1024104.
39. 39. Khan, A.R. & Khan, A. (2023). MaxViT-UNet: Multi-axis attention for medical image segmentation. arXiv preprint, arXiv:2305.08396.
40. 40. Shao, H., Zeng, Q., Hou, Q. & Yang, J. (2025). Mcanet: Medical image segmentation with multi-scale cross-axis attention. Machine Intelligence Research, 22(3), 437-451.
41. 41. Wu, H., Li, N., Zhang, J., Chen, S., Ng, M.K. & Long, J. (2024). Collaborative contrastive learning for hypergraph node classification. Pattern Recognition, 146, 109995.
42. 42. Sergio, G.C. & Lee, M. (2021). Stacked debert: All attention in incomplete data for text classification. Neural Networks, 136, 87-96.
43. 43. Chen, Z., Lou, K., Liu, Z., Li, Y., Luo, Y. & Zhao, L. (2024). Joint long and short span self-attention network for multi-view classification. Expert Systems with Applications, 235, 121152.
44. 44. Singh, P. (2023). Covid-19 chest X-ray dataset. https://www.kaggle.com/datasets/preetviradiya /covid19-radiography-dataset. Access date: 14.09.2025.
45. 45. Öter, E. & Doğan, Y. (2024). A comparative study on data balancing methods for alzheimer's disease classification. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(2), 489-501.