Lung Disease Prediction System using Deep Learning with Grad- CAM based Interpretability
Abstract
Lung diseases, particularly lung cancer, remain one of the leading causes of mortality worldwide. Early detection plays a crucial role in improving patient outcomes, but traditional diagnostic methods often face challenges related to accuracy, speed, and accessibility. This study presents a novel lung disease prediction system based on deep learning, utilizing Convolutional Neural Networks (CNNs) to classify chest CT scan images into 'Normal' and 'Lung Cancer' categories. The system incorporates Grad-CAM (Gradient-weighted Class Activation Mapping) for visual interpretability, enabling clinicians to better understand the regions in CT scans influencing the model's decision. A user-friendly web application is developed for real-time predictions, allowing users to upload CT images and receive instant results. The model, trained on a diverse set of datasets, achieves high accuracy, offering a valuable tool for early lung disease detection in clinical settings. This approach not only improves diagnostic accuracy but also enhances trust in AI-based medical systems by providing transparent visual explanations for model predictions. It achieved an accuracy of 97.50%, precision (0.98), recall (0.97), and F1-score (0.97).
References
Mamun, M., Farjana, A., Al Mamun, M., & Ahammed, M. S. (2022). Lung cancer prediction model using ensemble learning techniques and a systematic review analysis. In 2022 IEEE World AI IoT Congress (AIIoT) (pp. 187–193). IEEE. https://doi.org/10.1109/AIIoT54504.2022.9817326.
Makaju, S., Prasad, P. W. C., Alsadoon, A., Singh, A. K., & Elchouemi, A. (2018). Lung cancer detection using CT scan images. Procedia Computer Science, 125, 107–114. https://doi.org/10.1016/j.procs.2017.12.017.
International Agency for Research on Cancer. (2022). Global Cancer Observatory: Cancer today. IARC. https://gco.iarc.fr/ .
Ochoa-Ornelas, A., Ayala-Ruiz, J., Rivera-González, G., & Mariscal-Ramírez, I. (2025). Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach. Biomedical Signal Processing and Control, 87, Article 105193. https://doi.org/10.1016/j.bspc.2024.105193.
Saxena, P., Raj, A., & Tripathi, R. (2025). Hybrid deep convolution model for lung cancer detection with transfer learning. arXiv preprint arXiv:2501.02785. https://arxiv.org/abs/2501.02785.
Chaudhari, A., Patel, V., & Gajjar, K. (2025). Lung cancer detection using deep learning. arXiv preprint arXiv:2501.07197. https://arxiv.org/abs/2501.07197.
Bortty, M. R., Islam, M. R., & Rahman, M. A. (2024). Optimizing lung cancer risk prediction with advanced machine learning algorithms and techniques. Journal of Medical and Health Studies, 5(2), 24–35. https://doi.org/10.32996/jmhs.2024.5.2.3.
Islam, S. M., Kabir, M. H., & Chowdhury, F. (2024). Risk factors and early detection methods for lung cancer: A review of screening approaches. International Journal of Cancer Research, 20(1), 33–41.
Dutta, P., Sinha, R., & Ghosh, S. (2024). Integrating demographic risk assessment and LDCT imaging for early lung cancer prediction. Lung Cancer Journal, 102(4), 215–225.
Pathan, A. A., Shaikh, Z. M., & Ahmed, N. (2024). Challenges in traditional lung cancer risk models: The case for machine learning. Computational Oncology Reports, 9(3), 148–155.
Mohan, M., & Thayyil, J. (2023). Predictive lung cancer models: A review of PLCOm2012 and Bach model applicability. Clinical Predictive Analytics Journal, 7(1), 55–63.
Rajasekar, V., Natarajan, S., & Kumar, R. (2023). Combining histopathological and radiological data for improved lung cancer detection. Medical Image Analysis and Applications, 15(2), 87–95.
Deepapriya, R., Singh, P., & Narayanan, A. (2023). Evaluation of deep learning models for diagnosing lung diseases using medical imaging. Journal of Artificial Intelligence in Medicine, 11(3), 112–125.
Kaggle. (2025). Lung CT scan image datasets. https://www.kaggle.com/ .
Shorten, A., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1–48. https://doi.org/10.1186/s40537-019-0197-0.
Mamun, M., Mahmud, M. I., Meherin, M., & Abdelgawad, A. (2023, March). LCDCTCNN: Lung cancer diagnosis of CT scan images using CNN-based model. In 2023 10th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 205–212). IEEE. https://doi.org/10.1109/SPIN56039.2023.1011349.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://arxiv.org/abs/1409.1556.
Mandrekar, J. (2010). Receiver operating characteristic curve in diagnostic test assessment. Journal of Thoracic Oncology, 5(9), 1315–1316. https://doi.org/10.1097/JTO.0b013e3181ec173d.
Streamlit Inc. (2025). Streamlit — The fastest way to build data apps in Python. https://streamlit.io/ .
Selvaraju, R. R., Cogswell, M., Das, A., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 618–626). https://doi.org/10.1109/ICCV.2017.74.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?”: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Sustainable Development Through AI, ML and IoT
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.