A Comprehensive Liver Tumor Detection and Stages Classification Using Deep Learning and Image Processing Techniques

This research presents a deep learning framework designed to automatically detect and classify liver tumors in CT images, leveraging Convolutional Neural Networks (CNNs). The suggested method includes a sequence of pre-processing steps, such as resizing images and enhancing contrast through histogram equalization. Additionally, a bilateral filter is applied for noise removal, followed by K-means image-based segmentation for improved localization. The CNN is then employed for binary classification, distinguishing between benign and malignant tumors with an accuracy of 98.88%. If the CNN identifies a tumor as malignant, a secondary CNN-based classification system is employed to further categorize the malignant tumors into different stages: Early Stage, Intermediate Stage, and Metastatic Stage with an accuracy of 98.72%. This multi-step approach not only automates tumor detection but also provides a finer-grained analysis of malignant cases, offering valuable insights into the progression of liver tumors. The methodology combines advanced image processing techniques with deep learning classification, showcasing a comprehensive framework for efficient and detailed liver tumor analysis in medical imaging.