Detection of Liver Tumors in CT Scans Using Machine Learning and Texture Analysis

Abstract: Liver cancer is a major global health concern, demanding early and accurate detection for effective treatment. This study proposes an automated framework to detect and classify liver tumors from CT scan images using a combination of image preprocessing, segmentation, texture and shape feature extraction, and deep learning classification. Utilizing ResUNet for segmentation and ResNet50 for classification, the system distinguishes between benign and malignant tumors with high accuracy. The model was trained and evaluated using a publicly available dataset, demonstrating robust performance metrics and offering a valuable tool for assisting radiologists in clinical diagnostics.