This document describes a computer-aided diagnosis system for detecting liver cancer in early stages from CT chest images. The system uses a Hidden Markov Model (HMM) for classification. It involves preprocessing the CT image through segmentation, noise removal and morphological operations. Features are then extracted and classified using HMM. The system achieved a high detection rate of 96.5% on 100 cases, outperforming other methods. This automated early detection system could help reduce risks for liver cancer patients by enabling earlier medical treatment.