Lung cancer is one of the leading causes of cancer-related mortality worldwide. Early detection and accurate diagnosis are crucial for improving treatment efficacy and patient prognosis. However, traditional histopathological analysis is complex, time-consuming, and heavily reliant on the expertise of pathologists. In this study, we propose a lung cancer detection and classification model leveraging advanced deep learning techniques, including InceptionV3, ConvNet-Tiny, ResNet50, and DenseNet201, to extract critical features from histopathological images, thereby enhancing diagnostic accuracy. Conversely, recent related studies have primarily utilized the Grad-CAM technique to identify the most affected regions. In this study, we integrate Explainable AI techniques, specifically Grad-CAM and LIME, to visualize the key regions the model focuses on when making predictions. This approach provides deeper insights into the model’s decision-making process, aiding medical professionals in result interpretation. According to experimental results, the proposed model achieves an accuracy of up to 99% in lung cancer prediction.