Enhancing Clinical Predictability in Lung Disease Diagnosis Using Deep Learning on Chest X-Rays

Muhammad Qasim Shah; Nafey Ahmed; Rabia Tehseen; Uzma Omer

Authors

Muhammad Qasim Shah Department of Data Science, University of Central Punjab, Lahore, Pakistan
Nafey Ahmed Department of Data Science, University of Central Punjab, Lahore, Pakistan
Rabia Tehseen Department of Computer Science, University of Central Punjab, Lahore, Pakistan
Uzma Omer Department of Information Sciences, University of Education, Lahore, Pakistan

Keywords:

Deep Learning, Medical Image Classification, Transfer Learning, VGG16, CNN, Disease Diagnosis

Abstract

To increase diagnostic efficiency and accuracy, automated disease classification using medical images has become more important. To classify diseases based on labeled image data, this study investigates the use of several deep learning architectures, such as adapted convolutional neural networks (CNN), VGG16, ResNet50, and EfficientNetB0. The models were evaluated on accuracy, loss, and specific performance metrics using a rigorous training protocol and transfer learning. According to experimental results, VGG16 outperforms other models with the highest validation accuracy of approximately 97.6%. Simple CNNs also achieved competitive performance. Under the current training conditions, more complex models such as ResNet50 and EfficientNetB0 perform worse, indicating the need for further tuning or larger data sets. In addition to highlighting the effectiveness of pre-trained models in medical image classification tasks, this work provides a framework for comparative analysis. To improve clinical applicability, future directions include the integration of interpretability, advanced refinements, and dataset expansion.

References

Marly van Assen, Mohammadreza Zandehshahvar, Hossein Maleki, Yashar Kiarashi, Timothy Arleo, “COVID-19 pneumonia chest radiographic severity score: variability assessment among experienced and in-training radiologists and creation of a multireader composite score database for artificial intelligence algorithm development,” Br J Radiol, vol. 95, 2022, doi: 10.1259/bjr.20211028.

Arjun Nair, Alexander Procter, Steve Halligan, Thomas Parry, “Chest radiograph classification and severity of suspected COVID-19 by different radiologist groups and attending clinicians: multi-reader, multi-case study,” Eur Radiol, vol. 33, no. 3, pp. 2096–2104, 2023, [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/36282308/

Dana Li, Lea Marie Pehrson, Lea Tøttrup, Marco Fraccaro, “Inter- and Intra-Observer Agreement When Using a Diagnostic Labeling Scheme for Annotating Findings on Chest X-rays-An Early Step in the Development of a Deep Learning-Based Decision Support System,” Diagnostics, vol. 12, no. 12, 2022, [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/36553118/

Lea Marie Pehrson, Dana Li, “Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme,” Diagnostics, vol. 15, no. 7, p. 902, 2025, doi: https://doi.org/10.3390/diagnostics15070902.

G. R. John T. Murchison, “Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population,” PLoS One, vol. 17, no. 5, 2022, [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/35511758/

S. J. Raheel Siddiqi, “Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey,” J. Imaging, vol. 10, no. 8, p. 176, 2024, [Online]. Available: https://www.mdpi.com/2313-433X/10/8/176

M. B. Jakub Kufel, “Multi-Label Classification of Chest X-ray Abnormalities Using Transfer Learning Techniques,” J. Pers. Med., vol. 13, no. 10, 2023, [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/37888037/

K. A. & S. S. Sukhendra Singh, Manoj Kumar, Abhay Kumar, Birendra Kumar Verma, “Efficient pneumonia detection using Vision Transformers on chest X-rays,” Sci. Rep., vol. 14, no. 2487, 2024, doi: https://doi.org/10.1038/s41598-024-52703-2.

M. J. I. Muhammad Aasem, “Toward explainable AI in radiology: Ensemble-CAM for effective thoracic disease localization in chest X-ray images using weak supervised learning,” Front. big Data, 2024, [Online]. Available: https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1366415/full

B. B. Izegbua E. Ihongbe ,Shereen Fouad ,Taha F. Mahmoud,Arvind Rajasekaran, “Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens,” PLoS One, 2024, doi: https://doi.org/10.1371/journal.pone.0308758.

H. A. J. Mona Hmoud Al-Sheikh, Omran Al Dandan, Ahmad Sami Al-Shamayleh, “Multi-class deep learning architecture for classifying lung diseases from chest X-Ray and CT images,” Sci. Rep., vol. 13, no. 19373, 2023, [Online]. Available: https://www.nature.com/articles/s41598-023-46147-3

M. A. Mehdi Neshat, “Hybrid Inception Architecture with Residual Connection: Fine-tuned Inception-ResNet Deep Learning Model for Lung Inflammation Diagnosis from Chest Radiographs,” Procedia Comput. Sci., vol. 235, pp. 1841–1850, 2024, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1877050924008512

M. M. Muhammad Ahmad, Sardar Usman, Ildar Batyrshin, “Automated diagnosis of lung diseases using vision transformer: a comparative study on chest x-ray classification,” arXiv:2503.18973, 2025, [Online]. Available: https://arxiv.org/abs/2503.18973

S. G. Burcu Oltu, “Automated classification of chest X-rays: a deep learning approach with attention mechanisms,” BMC Med. Imaging, vol. 25, no. 71, 2025, [Online]. Available: https://link.springer.com/article/10.1186/s12880-025-01604-5

Iyad Sultan, Hasan Gharaibeh, “LungVisionNet: A Hybrid Deep Learning Model for Chest X-Ray Classification—A Case Study at King Hussein Cancer Center (KHCC),” Technologies, 2025, [Online]. Available: https://www.semanticscholar.org/paper/LungVisionNet%3A-A-Hybrid-Deep-Learning-Model-for-at-Sultan-Gharaibeh/115225758f1887b002b801860ce9346296e62fe2

Yilin Yao, Yinghan Li, Shirong Zheng, Taoyu Zhu, “Deep Learning Models for Multi-Class Pneumonia Detection in Chest X-Rays: A Comparative Study of VGG16, MobileNet, and ResNet152,” Comput. Simul. Appl., 2025, [Online]. Available: https://journal.whioce.com/index.php/csa/article/view/916

C. T. P. Rahul Kumar, “Enhanced Multi-Model Deep Learning for Rapid and Precise Diagnosis of Pulmonary Diseases Using Chest X-Ray Imaging,” Diagnostics, vol. 15, no. 3, p. 248, 2025, [Online]. Available: https://www.mdpi.com/2075-4418/15/3/248

H. M. Bouthaina Slika, Fadi Dornaika, “Lung pneumonia severity scoring in chest X-ray images using transformers,” Med. Biol. Eng. Comput., vol. 62, pp. 2389–2407, 2024, [Online]. Available: https://link.springer.com/article/10.1007/s11517-024-03066-3

A. T. Xiaoyang Fu, Rongbin Lin, Wei Du, “Explainable hybrid transformer for multi-classification of lung disease using chest X-rays,” Sci. Rep., vol. 15, 2025, [Online]. Available: https://www.nature.com/articles/s41598-025-90607-x

S. R. Sobia Nawaz, “Deep Learning ResNet101 Deep Features of Portable Chest X-Ray Accurately Classify COVID-19 Lung Infection,” Comput. Mater. Contin., vol. 75, no. 3, 2023, [Online]. Available: https://www.techscience.com/cmc/v75n3/52600/html