AI-Powered Lung Disease Detection Using Deep Learning on Chest X-Rays

Abstract

This paper presents an AI-powered approach for detecting lung diseases using deep learning techniques applied to chest X-ray images. The proposed system leverages convolutional neural networks (CNNs) to automatically learn discriminative features from medical images without manual intervention. Chest X-rays are preprocessed to enhance image quality and reduce noise before being fed into the model. The deep learning model is trained to classify multiple lung conditions such as pneumonia, tuberculosis, COVID-19, and normal cases. Experimental results demonstrate high accuracy, sensitivity, and specificity, indicating reliable diagnostic performance. The system reduces dependency on radiologists for initial screening and supports faster medical decision-making. Automation of lung disease detection helps in early diagnosis and timely treatment. The proposed method is cost-effective and suitable for large-scale clinical deployment. Overall, the study highlights the potential of AI in improving healthcare diagnostics.The system can be integrated into existing hospital workflows to assist medical professionals in routine screenings. By providing quick and accurate predictions, it helps reduce workload and diagnostic delays. Future enhancements may include training on larger datasets and extending the model to detect additional respiratory diseases.

Introduction

Lung diseases such as pneumonia, tuberculosis, and COVID-19 are major causes of global illness and mortality, making early and accurate diagnosis essential. Chest X-rays are widely used due to their low cost and availability, but manual interpretation is time-consuming and dependent on expert radiologists. Advances in artificial intelligence, particularly deep learning with Convolutional Neural Networks (CNNs), offer an effective solution for automated and accurate lung disease detection.

This project presents an AI-powered system that detects lung diseases from chest X-ray images. The system applies image preprocessing techniques to enhance quality and uses a pre-trained ResNet-based CNN to classify X-rays into Normal, COVID-19, Pneumonia, and Tuberculosis categories. To improve transparency and trust, Grad-CAM is integrated to visually highlight the regions of the X-ray that influence the model’s predictions.

The system is implemented as a web-based application using Streamlit, allowing users to upload X-ray images and receive real-time predictions with confidence scores and visual explanations. The workflow includes image resizing, normalization, model inference, probability estimation via softmax, and Grad-CAM heatmap generation.

Results demonstrate accurate classification and effective visualization of disease-relevant lung regions, showing the system’s potential as a clinical decision-support tool. Overall, the study highlights the value of deep learning in improving diagnostic efficiency, enabling early detection, supporting large-scale screening, and assisting healthcare professionals in lung disease diagnosis.

Conclusion

This project successfully demonstrates the effectiveness of deep learning techniques in detecting lung diseases from chest X-ray images. By leveraging a trained convolutionalneuralnetwork,thesystem accuratelyclassifiesX-rays intonormalanddisease categories, reducing manual diagnostic effort and minimizing the chances of human error.The integration of image preprocessing and automated prediction ensures consistent and reliable results.

References

[1] R. Sriramkumar, K. Selvakumar, and J. Jegan, “Advances in AI for pulmonary disease diagnosis using lung X-ray,” International Journal of Artificial Intelligence in Healthcare, 2024. [2] M. Neshata, M. Ahmed, and H. Askar, “Hybrid inception architecture with residual connection: Fine-tuned Inception-ResNet deep learning model for lung inflammation diagnosis from chest radiographs,” Biomedical Signal Processing and Control, vol. 88, 2024. [3] S. T. H. Kieu, A. Bade, and M. H. A. Hijazie, “A surveyof deep learning for lung disease detection on medical images,” Journal of Healthcare Engineering, 2023. [4] L. Visuña, D. Yang, J. G. Blas, and J. Carretero, “Computer-aided diagnostic for classifying chest X-ray images using deep ensemble learning,” Applied Soft Computing, vol. 121, 2022. [5] S. Bharati, P. Podder, and M. R. H. Mondal, “Hybrid deep learning for detecting lung diseases from X-ray images,” Informatics in Medicine Unlocked, vol. 20, 2020. [6] M. H. Al Sheikh, O. Al Dandan, A. S. Al Shamayleh, H. A. Jalab, and R. W. Ibrahim, “Multi-class deep learning architecture forclassifyinglungdiseases from chest X-rayand CT images,” Computers in Biology and Medicine, vol. 158, 2023. [7] M. J. P. Priyadarsini, K. Kotecha, G. K. Rajini, and K. Hariharan, “Lung diseases detection using various deep learning algorithms,” Journal of Medical Systems, vol. 47, no. 6, 2023. [8] X. Fu, R. Lin, W. Du, A. Tavares, and Y. Liang, “Explainable hybrid transformer for multi-classification of lung disease using chest X-rays,” IEEE Journal of Biomedical and Health Informatics, 2024. [9] M. Atoum, “THORAMO: An AI-powered system for automated detection and prioritization of thoracic diseases from chest X-rays,” Artificial Intelligence in Medicine, 2024. [10] A. R. T. Abdulahi, R. O. Ogundokun, A. R. Adenike, M. A. Shah, and Y. K. Ahmed, “PulmoNet: A novel deep learning-based pulmonary diseases detection model,” Diagnostics, vol. 14, no. 3, 2024.

Copyright

Copyright © 2026 Mrs. Shylaja L N, Disha C M, Keerthana B K, Sahana C M, Tasmiya Khadar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.