<![CDATA[Lung cancer remains one of the leading causes of mortality worldwide, highlighting the importance of early and accurate detection. This study proposes a deep learning-based approach for lung cancer classification using the MobileNetV2 architecture on CT-scan images. Two experimental scenarios were investigated: transfer learning with a frozen base model and fine-tuning by unfreezing selected layers. The dataset was compiled from publicly available sources and balanced to address class imbalance. The model was trained using the Stochastic Gradient Descent (SGD) optimizer and evaluated using accuracy, precision, recall, and F1-score. The results demonstrate that the fine-tuning strategy achieves superior performance across most evaluation metrics compared to transfer learning. In particular, recall shows a significant improvement, indicating enhanced capability in detecting positive cancer cases, although accompanied by a slight decrease in precision. The F1-score also improves, reflecting a better balance between precision and recall. These findings suggest that fine-tuning enhances feature representation and improves classification performance within the experimental setting. However, the results are limited to the dataset used in this study, and further validation on larger and clinically representative datasets is required before considering real-world medical applications.]]>
Copyrights © 2026
