X-ray imaging is used extensively in detecting diseases of the chest; however, this is affected by factors that reduce classification accuracy, such as blurred images and significant class imbalance. In this paper, a deep learning model is proposed for classification of images containing multiple chest diseases. The images used were a combination of images from the NIH ChestX-ray14 dataset, containing 112,120 images of 14 diseases, and images containing only COVID-19 cases. Three baseline architectures were used, namely, ResNet50 as a reference model, EfficientNet-B5, and CoAtNet-0-rw. The class imbalance was reduced using the Asymmetric Loss (ASL) algorithm, as well as other training optimization techniques. In addition, a data purification phase was included to correct any tags that were inconsistent, thus preventing model confusion. The best model was EfficientNet-B5, which had an AUROC of 0.862. The maximum accuracy was obtained by using CoAtNet-0-rw, which had an accuracy of 95%. In addition, a hybrid model was proposed, which used a combination of deep model features and an SVM classifier. The model had good generalizability, as observed from the evaluation using an external data source, VinDr-CXR.
D. Huang, X. Lian, F. Song, H. Ma, Z. Lian, Y. Liang, T. Qin, W. Chen, and S. Wang, “Clinical features of severe patients infected with 2019 novel coronavirus: a systematic review and meta-analysis,” Annals of Translational Medicine, vol. 8, no. 9, Art. no. 576, May 2020, [Online]. Available: https://doi.org/10.21037/atm-20-2124.
Y. Chen, Y. Wan, and F. Pan, “Enhancing multi-disease diagnosis of chest X-rays with advanced deep-learning networks in real-world data,” Journal of Digital Imaging, Mar. 2023, [Online]. Available: https://doi.org/10.1007/s10278-023-00801-4.
F. Li et al., “Lesion-aware convolutional neural network for chest radiograph classification,” Clinical Radiology, vol. 76, pp. 155.e1-155.e14, 2021, [Online]. Available: https://doi.org/10.1016/j.crad.2020.08.027.
X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, “ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778.
M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. 36th Int. Conf. Mach. Learn. (ICML), Long Beach, CA, USA, 2019, pp. 6105-6114.
Z. Dai, H. Liu, Q. V. Le, and M. Tan, “CoAtNet: Marrying convolution and attention for all data sizes,” in Proc. 35th Int. Conf. Neural Information Processing Systems (NeurIPS), 2021.
S. Banerjee, R. Misra, M. Prasad, E. Elmroth, and M. H. Bhuyan, “Multi-diseases classification from chest X-ray: A federated deep learning approach,” in Proc. Int. Conf. Artificial Intelligence (AI 2020), Lecture Notes in Computer Science, vol. 12576, Springer, Dec. 2020, pp. 3-15, [Online]. Available: https://doi.org/10.1007/978-3-030-64984-5_1.
F. S. Yimer, A. W. Tessema, and G. L. Simegn, “Multiple lung diseases classification from chest X-ray images using deep learning approach,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 10, no. 5, pp. 2936-2946, Sep.-Oct. 2021, [Online]. Available: https://doi.org/10.30534/ijatcse/2021/021052021.
A. Kabiraj, T. Meena, P. B. Reddy, and S. Roy, “Detection and classification of lung disease using deep learning architecture from X-ray images,” in Proc. Int. Symp. Vis. Comput. (ISVC 2022), Lecture Notes in Computer Science, vol. 13598, Springer, Dec. 2022, pp. 444-455, [Online]. Available: https://doi.org/10.1007/978-3-031-20713-6_34.
Md. Nahiduzzaman, Md. R. Islam, and R. Hassan, “ChestXray6: Prediction of multiple diseases including COVID-19 from chest X-ray images using convolutional neural network,” Expert Systems with Applications, vol. 211, Art. no. 118576, 2023, [Online]. Available: https://doi.org/10.1016/j.eswa.2022.118576.
Y. Gu, R. Shi, S. Yang, L. Yang, B. Zhang, J. Wang, X. Lu, J. Li, X. Liu, Y. Zhao, D. Yu, S. Tang, and Q. He, “Multi-disease X-ray image classification of the chest based on global and local fusion adaptive networks,” Current Medical Imaging, vol. 20, Art. no. e15734056291283, 2024, [Online]. Available: https://doi.org/10.2174/0115734056291283240808045952.
M. Ucan, B. Kaya, O. Aygun, M. Kaya, and R. Alhajj, “Comparison of EfficientNet CNN models for multi-label chest X-ray disease diagnosis,” PeerJ Computer Science, vol. 11, Art. no. e2968, 2025, [Online]. Available: https://doi.org/10.7717/peerj-cs.2968.
K. Divya Reddy and A. Patil, “CXR-MultiTaskNet: A unified deep learning framework for joint disease localization and classification in chest radiographs,” Scientific Reports, vol. 15, Art. no. 32022, 2025, [Online]. Available: https://doi.org/10.1038/s41598-025-16669-z.
I. D. Penman, S. H. Ralston, M. W. J. Strachan, and R. P. Hobson, Davidson’s Principles and Practice of Medicine, 24th ed. London, UK: Elsevier, 2023.
J. S. Klein and M. L. Rosado-de-Christenson, “A Systematic Approach to Chest Radiographic Analysis,” in Diseases of the Chest, Breast, Heart and Vessels 2019-2022, J. Holder et al., Eds., IDKD Springer Series, Springer, 2019, [Online]. Available: https://doi.org/10.1007/978-3-030-11149-6_1.
H. Q. Nguyen, K. Lam, L. T. Le et al., “VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations,” Scientific Data, vol. 9, no. 1, Art. no. 429, Jul. 2022, [Online]. Available: https://doi.org/10.1038/s41597-022-01498-w.
J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7132-7141.
T. Ridnik, E. Ben-Baruch, N. Zamir, A. Noy, I. Friedman, M. Protter, and L. Zelnik-Manor, “Asymmetric loss for multi-label classification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 82-91.
