Interpretable AI for Liver Cancer Detection: Cascaded CNN & GLCM Integration

Liver cancer has significantly high mortality, especially in regions such as Africa and Asia. Early detection enhances treatment options, but indications are frequently not apparent until advanced stages. This research introduces an explainable AI (XAI) approach using a cascaded Convolutional Neural Network (CNN) combined with Gray Level Co-occurrence Matrix (GLCM)-based texture features to segregate non-cancerous from malicious tumors. The CLD system was used for assessment, and the approach was examined using the TCIA dataset, demonstrating higher accuracy and interpretability compared to prevailing techniques. XAI methods, such as feature importance and model visualization, were employed to provide details on the decision-making process of the model, ensuring transparency and reliability in clinical applications.