AI-based Diagnostic System for Chest X-rays: A Multi-Labeled Classification Approach using Deep Learning

Deepak Raj Sharma

doi:10.70454/JRICST.2026.30103

Authors

Deepak Raj Sharma Professor & Dean, College of Science and Technology Surajmal University, Kichha Uttrakhand, India Author

DOI:

https://doi.org/10.70454/JRICST.2026.30103

Keywords:

Deep learning, Multi-label classification, Chest X-ray, Transfer learning, DenseNet, Medical image analysis

Abstract

Although chest X-rays (CXRs) are still a vital diagnostic tool for detecting thoracic disease, their interpretation can be challenging because of their multilevel findings and contradictory visual patterns. As a result, we examine how well deep convolutional neural networks (CNNs) with transfer learning perform automated multi-label classification of CXRs. Extensive preprocessing and augmentation techniques were used to address class imbalance and normalise image quality using the CheXpert dataset. Under consistent experimental conditions, several CNN architectures, including CustomNet, DenseNet121, ResNet50, InceptionV3, and VGG16, were trained and evaluated. With an AUROC of 0.78 and an accuracy of 87% on test data, DenseNet121 performs significantly better than all other models, according to a comparative analysis of AUROC and accuracy. Additional evaluation by disease category on an individual basis showed excellent performance for pleural effusion (AUROC 0.93) and lung opacity (AUROC 0.91). These results indicate the promise of Dense Net-based architectures to deliver accurate, automated diagnostic assistance to clinical radiology. The work emphasizes the utility of transfer learning in enhancing generalization with sparse labeled data and offers pragmatic guidance to model choice in the analysis of medical images.

Downloads

Download data is not yet available.

References

[1] Imaging and Radiology: MedlinePlus Medical Encyclopedia. Available: https://medlineplus.gov/ency/article/007451.ht

[2] J. Irvin, P. Rajpurkar, M. Ko, Y. Yu, S. Ciurea-Ilcus, C. Chute, H. Marklund et al., “CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison,” Proc. AAAI Conf. Artif. Intell., vol. 33, pp. 590–597, 2019.

[3] A. Nair, U. Nair, P. Negi, P. Shahane, and P. Mahajan, “Detection of diseases on chest X-ray using deep learning,” Cikitusi J. Multidiscip. Res., vol. 6, no. 5, pp. 298–305, 2019.

[4] N. Wall, M. Palanisamy, and J. Santerre, “Automated pleural effusion detection on X-rays,” SMU Data Sci. Rev., vol. 2, no. 2, p. 15, 2019.

[5] A. Madani, M. Moradi, A. Karargyris, and T. Syeda-Mahmood, “Chest X-ray generation and data augmentation for cardiovascular abnormality classification,” in Proc. Med. Imag. 2018: Image Process., vol. 10574, pp. 415–420, 2018.

[6] 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, pp. 2097–2106.

[7] I. M. Baltruschat, H. Nickisch, M. Grass, T. Knopp, and A. Saalbach, “Comparison of deep learning approaches for multi-label chest X-ray classification,” Sci. Rep., vol. 9, no. 1, p. 6381, 2019.

[8] “Deep transfer learning for the multilabel classification of chest X-ray images,” Diagnostics, vol. 12, no. 6, p. 1457, 2022.

[9] T. H. Nguyen-Mau, T. L. Huynh, T. D. Le, H. D. Nguyen, and M. T. Tran, “Advanced augmentation and ensemble approaches for classifying long-tailed multi-label chest X-rays,” 2023.

[10] L. Van Der Maaten and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700–4708.

[11] G. Holste, S. Wang, Z. Jiang, T. C. Shen, G. Shih, R. M. Summers, et al., “Long-tailed classification of thorax diseases on chest X-ray: A new benchmark study,” in MICCAI Workshop on Data Augmentation, Labelling, and Imperfections, Cham: Springer Nature Switzerland, 2022, pp. 22–32.

[12] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778.

[13] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826.

[14] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. 25th Int. Conf. Neural Inf. Process. Syst. (NIPS), vol. 1, pp. 1097–110