ADVANCED DETECTION OF BRAIN AND LUNG TUMORS THROUGH EXPLAINABLE AI APPROACHES

Lung and brain cancers remain some of the top causes of death around the globe. Improving patient outcomes is reliant on early detection. Conventional imaging relies on time-consuming manual assessments, creating opportunities for errors. This study presents a hybrid deep learning framework along with explainable artificial intelligence (XAI) methods for improved detection and classification of brain and lung tumours. Brain tumours are detected using MRI, while lung tumours are identified with CT scans. The proposed framework merges convolutional neural networks with XAI techniques such as Grad-CAM and SHAP to provide transparent rationales for automated predictions. The developed models defined and improved new accuracy, precision, recall, and F1-score benchmarks within the study. Clinicians are provided with visual explanations, which fosters trust and assures decision-making. This approach is designed for early diagnosis and effective treatment planning.