Lung Cancer Detection Using Deep Learning and Explainable Methods

Lung cancer is one of the most prevalent deadly diseases and it can extend to the rest of the human body. One way to detect it in CT scan images is by using deep learning models. Explaining these models by XAI techniques and radiologists make the results trusted for medical use. In this paper, the deep learning models inceptionV3and ResNet50 were used to classify CT scans of lungs for the presence of cancer. The models were trained on a Kaggle dataset that is pre-processed and augmented. It was able to accurately detect lung cancer in new patients. Additionally, an XAI model was used to explain the decision-making process of the deep learning model, providing insights into which features of the CT scan were most important for the model's diagnosis. ResNet50 achieved the highest performance with 100% accuracy on testing images, and InceptionV3 got 99.92%. LIME and GRAD-CAM explained the model's performance by highlighting the most important features for each model. On the other hand, radiologists provided insight on whether the deep learning and XAI models are correct by determining the cancer region in each image and point out the model's misclassification. The results show that the radiologist's diagnosis is important even though the model's accuracy is high.