A classification framework for diagnosis of focal liver diseases

Computer-aided detection/diagnosis (CAD) systems are critical for doctors to understand the medical images and to improve the accuracy of detection/diagnosis of various diseases. The goal of this paper is to propose a classification framework for diagnosing different focal liver diseases based on ultrasound (US) images. Ultrasound medical imaging is one of the most common modality, which is used in diagnostic systems because of its safety and cost effectiveness. In this paper, we introduced a framework for a CAD system to diagnosing three classes of focal liver diseases, which are Cyst, Hemangioma (HEM), and Hepatocellular Carcinoma (HCC). The proposed system begins with a preprocessing step to make enhancement and noise removal of US images using a median filter. The segmentation of the liver lesions regions is done using level set method followed by the fuzzy c-mean clustering algorithm. Finally, we have used a multi-support vector machine (multi-SVM) classifier to diagnosis the classes of the focal liver diseases. By using 10-fold cross validation method, we have got an overall classification accuracy of 96.5%. Our proposed system is compared with some state of the art techniques. The experimental results show that the proposed system gives better overall accuracy than the other tested techniques.