Differential Diagnosis of Infectious Respiratory Diseases via Hybrid Deep Learning: Clinical Evaluation of COVID-19, Pneumonia, and Tuberculosis on Chest Radiography
Main Article Content
Abstract
The timely and precise differentiation of infectious respiratory diseases is vital in ensuring optimal patient outcomes and reinforcing public health infection control measures. The present study presents a precise hybrid deep learning architecture for the classification of infectious respiratory diseases based on chest X-ray images. The model was able to classify images into COVID-19, Normal, Pneumonia, and Tuberculosis. The model was able to perform a comprehensive analysis of localized pathological features in the images through the employment of a seg-mental random patch-based sampling strategy. The model also employed a pretrained ResNet-18 model in combination with a Context Pooling layer and Long Short-Term Memory networks. The model was able to achieve a remarkable 96% overall accuracy on a comprehensive dataset of 7,132 images. Notably, the model achieved a remarkable level of diagnostic sensitivity for high-priority communicable diseases, including a 99% F1-score for Tuberculosis and 95% for COVID-19 after only three training epochs. The results indicate that the inclusion of spatial-temporal sequence modeling results in a potent and efficient Clinical Decision Support System (CDSS), which can aid in automated screening and triage in resource-constrained settings where access to radiological expertise may be limited.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] S. Menon and K. Koura, “Artificial intelligence for tuberculosis control: a scoping review of applications in public health,” J. Glob. Health, vol. 15, 2025, doi: 10.7189/jogh.15.04192.
[2] Z.-L. Han et al., “A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest X-ray imaging,” J. Thorac. Dis., vol. 17, no. 5, 2025, doi: 10.21037/jtd-2025-604.
[3] D. Meedeniya, H. Kumarasinghe, S. Kolonne, C. Fernando, I. D. la T. Díez, and G. Marques, “Chest X-ray analysis empowered with deep learning: A systematic review,” Appl. Soft Comput., vol. 126, p. 109319, Sep. 2022, doi: 10.1016/j.asoc.2022.109319.
[4] D. Palaniappan et al., “YOLO in Healthcare: A Comprehensive Review of Detection Architectures, Domain Applications, and Future Innovations,” IEEE Access, vol. 13, pp. 145714–145735, 2025, doi: 10.1109/ACCESS.2025.3599358.
[5] J. Chi, J. Zhao, S. Wang, X. Yu, and C. Wu, “LGDNet: local feature coupling global representations network for pulmonary nodules detection,” Med. Biol. Eng. Comput., vol. 62, no. 7, pp. 1991–2004, Jul. 2024, doi: 10.1007/s11517-024-03043-w.
[6] A. Shimazaki et al., “Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method,” Sci. Rep., vol. 12, no. 1, p. 727, 2022, doi: 10.1038/s41598-021-04667-w.
[7] C.-F. Chen et al., “A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography,” Sci. Rep., vol. 14, no. 1, p. 14917, Jun. 2024, doi: 10.1038/s41598-024-65703-z.
[8] A. Abdelhamid, A. El-Ghamry, E. H. Abdelhay, M. M. Abo-Zahhad, and H. E.-D. Moustafa, “Improved pulmonary embolism detection in CT pulmonary angiogram scans with hybrid vision transformers and deep learning techniques,” Sci. Rep., vol. 15, no. 1, p. 31443, Aug. 2025, doi: 10.1038/s41598-025-16238-4.
[9] H. Iqbal, A. Khan, N. Nepal, F. Khan, and Y.-K. Moon, “Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review,” 2024. doi: 10.3390/electronics13234688.
[10] B. Ozdemir, E. Aslan, and I. Pacal, “Attention Enhanced InceptionNeXt-Based Hybrid Deep Learning Model for Lung Cancer Detection,” IEEE Access, vol. 13, pp. 27050–27069, 2025, doi: 10.1109/ACCESS.2025.3539122.
[11] R. Durgam, B. Panduri, V. Balaji, A. O. Khadidos, A. O. Khadidos, and S. Selvarajan, “Enhancing lung cancer detection through integrated deep learning and transformer models,” Sci. Rep., vol. 15, no. 1, p. 15614, May 2025, doi: 10.1038/s41598-025-00516-2.
[12] Z. Liu, “Medical and Industrial Visual Inspection,” Appl. Comput. Eng., vol. 196, pp. 38–46, 2025, doi: 10.54254/2755-2721/2025.LD28277.
[13] W. Xu, Y.-L. Fu, and D. Zhu, “ResNet and its application to medical image processing: Research progress and challenges,” Comput. Methods Programs Biomed., vol. 240, p. 107660, Oct. 2023, doi: 10.1016/j.cmpb.2023.107660.
[14] J. Xu, Y. Pan, X. Pan, S. Hoi, Z. Yi, and Z. Xu, “RegNet: Self-Regulated Network for Image Classification,” IEEE Trans. Neural Networks Learn. Syst., vol. 34, no. 11, pp. 9562–9567, Nov. 2023, doi: 10.1109/TNNLS.2022.3158966.
[15] Z. Ji, S. Ye, and X. Ma, “Sparse Coding Inspired LSTM and Self-Attention Integration for Medical Image Segmentation,” IEEE Trans. Image Process., vol. 33, pp. 6098–6113, 2024, doi: 10.1109/TIP.2024.3482189.
[16] M. Li, Y. Jiang, Y. Zhang, and H. Zhu, “Medical image analysis using deep learning algorithms,” Front. Public Heal., vol. Volume 11, no. November, pp. 1–28, 2023, doi: 10.3389/fpubh.2023.1273253.
[17] X. Ma, E. C. Ferguson, X. Jiang, S. I. Savitz, and S. Shams, “A multitask deep learning approach for pulmonary embolism detection and identification,” Sci. Rep., vol. 12, no. 1, p. 13087, 2022, doi: 10.1038/s41598-022-16976-9.