An Interpretable Deep Learning Framework for Multi-Class Lung Disease Diagnosis Using ConvNeXt Architecture

Muhammad Khalidin Basyir; Mhd Furqan; Aulia  Fadlan

doi:10.52436/1.jutif.2025.6.6.5404

Authors

Muhammad Khalidin Basyir Department of Computer Science, State Islamic University of North Sumatra, Indonesia
Mhd Furqan Department of Computer Science, State Islamic University of North Sumatra, Indonesia
Aulia Fadlan Master of Data Science Programme, Faculty of Computer Science and Information Technology, University of Malaya, Malaysia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.6.5404

Keywords:

Chest X-Ray, ConvNeXt, Deep Learning, Grad-CAM, Lung Disease

Abstract

Lung diseases remain a major global health challenge, requiring accurate and interpretable diagnostic systems to support timely detection and treatment. This study proposes a high-fidelity deep learning approach using the ConvNeXt architecture for automated multi-class classification of chest X-ray (CXR) images into five categories: Bacterial Pneumonia, Viral Pneumonia, COVID-19, Tuberculosis, and Normal. The methodology involved preprocessing 10.095 Kaggle-sourced images (normalization, CLAHE, augmentation, resizing) and training a ConvNeXt model for 70 epochs with the Adam optimizer. The model achieved strong performance with 92.66% validation accuracy, 86.32% test accuracy, a macro-average F1-score of 0.86, and a macro-average AUC of 0.99. Grad-CAM visualizations demonstrated the model's consistent focus on clinically relevant lung regions, significantly improving interpretability and clinical applicability. This study contributes to advancing interpretable AI methods for clinical decision support in medical imaging, offering a reliable and transparent framework for automated lung disease diagnosis.

Downloads

Download data is not yet available.

References

R. O. for the E. M. World Health Organization, “World TB Day 2025,” World Health Organization (WHO). Accessed: Aug. 28, 2025. [Online]. Available: https://www.emro.who.int/world-tb-day/2025/index.html

UNICEF, “Pneumonia,” UNICEF. Accessed: Aug. 28, 2025. [Online]. Available: https://data.unicef.org/topic/child-health/pneumonia/

H. Iqbal, A. Khan, N. Nepal, F. Khan, and Y. K. Moon, “Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review,” Electron., vol. 13, no. 23, pp. 1–24, 2024, doi: 10.3390/electronics13234688.

G. Kourounis, A. A. Elmahmudi, B. Thomson, J. Hunter, H. Ugail, and C. Wilson, “Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for medical professionals,” Postgrad. Med. J., vol. 99, no. 1178, pp. 1287–1294, 2023, doi: 10.1093/postmj/qgad095.

S. Tiwari, G. Jain, D. K. Shetty, M. Sudhi, J. M. Balakrishnan, and S. R. Bhatta, “A Comprehensive Review on the Application of 3D Convolutional Neural Networks in Medical Imaging,” Eng. Proc., vol. 59, no. 1, pp. 1–9, 2023, doi: 10.3390/engproc2023059003.

N. M. Pillai, S. Manimala, A. S. Rongali, A. Gugnani, A. S. Kumar, and G. V Sriramakrishnan, “Automated Classification of Medical Images Using Convolutional Neural Networks,” in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1–6. doi: 10.1109/ICCCNT61001.2024.10725642.

A. Souid, N. Sakli, and H. Sakli, “Classification and predictions of lung diseases from chest x‐ rays using mobilenet v2,” Applied Sciences, vol. 11, no. 6, 2021, doi: 10.3390/app11062751.

S. A. Hasanah, A. A. Pravitasari, A. S. Abdullah, I. N. Yulita, and M. H. Asnawi, “A Deep Learning Review of ResNet Architecture for Lung Disease Identification in CXR Image,” Applied Sciences, vol. 13, no. 24, 2023, doi: 10.3390/app132413111.

F. M. Javed Mehedi Shamrat et al., “LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images,” J. Pers. Med., vol. 12, no. 5, 2022, doi: 10.3390/jpm12050680.

N. Izdihar, S. B. Rahayu, and K. Venkatesan, “Comparison Analysis of CXR Images in Detecting Pneumonia Using VGG16 and ResNet50 Convolution Neural Network Model,” Int. J. Informatics Vis., vol. 8, no. 1, pp. 326–332, 2024, doi: 10.62527/joiv.8.1.2258.

Z. P. Jiang, Y. Y. Liu, Z. E. Shao, and K. W. Huang, “An improved VGG16 model for pneumonia image classification,” Applied Sciences, vol. 11, no. 23, 2021, doi: 10.3390/app112311185.

M. Bundea and G. M. Danciu, “Pneumonia Image Classification Using DenseNet Architecture,” Inf., vol. 15, no. 10, 2024, doi: 10.3390/info15100611.

Z. Liu, H. Mao, C. Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 11966–11976, 2022, doi: 10.1109/CVPR52688.2022.01167.

S. I. A. Stojnev D., “Preprocessing Image Data for Deep Learning,” in Sinteza 2020 - International Scientific Conference on Information Technology and Data Related Research, 2020, pp. 312–317. doi: 10.15308/Sinteza-2020-312-317.

S. Albert et al., “Comparison of Image Normalization Methods for Multi-Site Deep Learning,” Applied Sciences, vol. 13, no. 15, pp. 1–13, 2023, doi: 10.3390/app13158923.

R. Srikanth, B. Nagarjuna, K. Varshith, G. Supriya, and S. P. Reddy, “Enhancing of Night Time Vehicle Images using CLAHE Method,” in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1–8. doi: 10.1109/ICCCNT61001.2024.10725464.

E. Goceri, “Image Augmentation for Deep Learning Based Lesion Classification from Skin Images,” in 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 2020, pp. 144–148. doi: 10.1109/IPAS50080.2020.9334937.

H. Talebi and P. Milanfar, “Learning to Resize Images for Computer Vision Tasks,” Proc. IEEE Int. Conf. Comput. Vis., pp. 487–496, 2021, doi: 10.1109/ICCV48922.2021.00055.

C. Urrea, Y. Garcia-Garcia, and J. Kern, “Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance,” Biomedicines, vol. 12, no. 6, 2024, doi: 10.3390/biomedicines12061309.

K. Solanki, S. P. Singh, A. Yadav, V. Sharma, S. Awasthi, and S. Vats, “Enhancing Ophthalmic Diagnostics: CNNs in Cataract Detection,” in 2024 2nd International Conference on Disruptive Technologies (ICDT), 2024, pp. 842–846. doi: 10.1109/ICDT61202.2024.10489576.

S. Haji and A. Abdulazeez, “COMPARISON OF OPTIMIZATION TECHNIQUES BASED ON GRADIENT DESCENT ALGORITHM: A REVIEW PJAEE, 18 (4) (2021) COMPARISON OF OPTIMIZATION TECHNIQUES BASED ON GRADIENT DESCENT ALGORITHM: A REVIEW Comparison Of Optimization Techniques Based On Gradient Descent Al,” PalArch’s J. Archaeol. Egypt/ Egyptol., vol. 18, pp. 2715–2743, Jun. 2021.

G. Maillard, S. Arlot, and M. Lerasle, “Aggregated Hold-Out,” J. Mach. Learn. Res., vol. 22, no. 20, pp. 1–55, 2021, [Online]. Available: http://jmlr.org/papers/v22/19-624.html

E. Kristiani, Y. T. Tsan, P. Y. Liu, N. Y. Yen, and C. T. Yang, “Binary and Multi-Class Assessment of Face Mask Classification on Edge AI Using CNN and Transfer Learning,” Human-centric Comput. Inf. Sci., vol. 12, 2022, doi: 10.22967/HCIS.2022.12.053.

B. J. Erickson and F. Kitamura, “Magician’s Corner: 9. Performance Metrics for Machine Learning Models,” Radiol. Artif. Intell., vol. 3, no. 3, p. e200126, May 2021, doi: 10.1148/ryai.2021200126.

A. Mehra, Y. Zhang, and J. Hamm, “Test-time Assessment of a Model’s Performance on Unseen Domains via Optimal Transport,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., no. Ml, pp. 173–182, 2024, doi: 10.1109/CVPRW63382.2024.00022.

S. F. Hussain and M. M. Ashraf, “A novel one-vs-rest consensus learning method for crash severity prediction,” Expert Syst. Appl., vol. 228, p. 120443, 2023, doi: https://doi.org/10.1016/j.eswa.2023.120443.

D. Song et al., “A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: comparing with Grad-CAM,” Comput. Methods Programs Biomed., vol. 235, p. 107527, 2023, doi: https://doi.org/10.1016/j.cmpb.2023.107527.

S. Sattarzadeh, M. Sudhakar, K. N. Plataniotis, J. Jang, Y. Jeong, and H. Kim, “Integrated Grad-Cam: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks Via Integrated Gradient-Based Scoring,” in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 1775–1779. doi: 10.1109/ICASSP39728.2021.9415064.