DEEP LEARNING-BASED LUNG CANCER IMAGE ANALYSIS AND CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS

This project successfully developed a deep learning-based lung cancer image analysis system using a Convolutional Neural Network (CNN) for the automated classification of histopathological lung tissue images. The proposed model was implemented using TensorFlow and Keras and trained to classify images into six categories: Adenocarcinoma, Benign, Large Cell Carcinoma, Malignant, Normal, and Squamous Cell Carcinoma. Image preprocessing and data augmentation techniques were applied to improve the model's performance and generalization capability, while Early Stopping and Model Checkpoint were used to obtain the best-performing model. A user-friendly web application was developed using the Flask framework, enabling users to upload lung tissue images and receive instant predictions along with confidence scores and probability distribution charts. This provides an intuitive interface for automated image analysis and supports easier interpretation of the model's predictions. The experimental results demonstrate that the proposed CNN-based system is capable of accurately classifying lung cancer images and can serve as an effective decision-support tool for healthcare professionals. By reducing diagnosis time, improving consistency, and assisting in the early detection of lung cancer, the system has the potential to enhance clinical workflows and improve patient outcomes. Although the system is not intended to replace medical experts, it can provide reliable preliminary analysis to support informed medical decision-making. In the future, the system can be further enhanced by training on larger and more diverse datasets, adopting advanced deep learning architectures such as transfer learning and attention-based models, integrating explainable AI techniques for better model interpretability, and deploying the application on cloud or mobile platforms for real-time clinical use. These improvements can further increase the accuracy, robustness, and practical applicability of the proposed system.

1.    Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), 25, 1097–1105. 2.     LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324. 3.    Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press, Cambridge, MA. 4.    Chollet, F. (2021). Deep Learning with Python (2nd Edition). Manning Publications. 5.     Abadi, M., Agarwal, A., Barham, P., et al. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv:1603.04467. 6.    TensorFlow Developers. TensorFlow Documentation. https://www.tensorflow.org/ 7.    Keras Team. Keras Documentation. https://keras.io/ 8.       Flask Documentation. Flask Web Framework Documentation. https://flask.palletsprojects.com/ 9.    Han, J., Kamber, M., & Pei, J. (2012). Data Mining: Concepts and Techniques (3rd Edition). Morgan Kaufmann. 10.   Szeliski, R. (2022). Computer Vision: Algorithms and Applications (2nd Edition). Springer.