Lung cancer cell classification using deep learning models

Abstract

This project report explores the application of Convolutional Neural Networks (CNNs) and transfer learning for the detection and classification of lung cancer using histopathological images. Lung cancer is a leading cause of cancer-related deaths worldwide, and early, accurate detection is critical for effective treatment. This study leverages the ResNet50 architecture, a state-of-the-art CNN model, to classify lung cancer images. Transfer learning techniques are employed to fine-tune the pre-trained ResNet50 model, enhancing its performance with the lung cancer dataset. Rigorous hyperparameter tuning and model evaluation were conducted to optimize detection accuracy, precision, recall, and F1-score. The experimental results demonstrated that the ResNet50 model achieved superior performance compared to other models, indicating its effectiveness in accurately detecting lung cancer. This research underscores the potential of advanced CNN architectures in improving lung cancer diagnostics and suggests future work integrating additional imaging modalities and sophisticated data augmentation techniques.