Hepatic diseases diagnosis using contrast and non-contrast CT images

In the diagnosis of hepatic diseases, "Contrast-Enhanced CT" (CECT) and "Non-Contrast CT" (NCT) are usually simultaneously adopted. Based on their individual features and their differences, the type of hepatic disease can be determined. However, this diagnosis relies heavily on radiologists' experiences, resulting that the diagnosis accuracy limited. To solve this problem, a computerized system embedded with new techniques to quantify tumor features is particularly designed in this paper, to serve as an assistance to doctors. The proposed system consists of a feature-extractor and a fuzzy-diagnosis engine. The feature-extractor is to capture tumor image features from both CECT and NCT images and quantify them into determinate objective values. The captured image features are then served as the inputs to the fuzzy-diagnosis engine which bases on established rules making diagnosis decisions. The system has been tested using 131 sets of image data which are to be classified into 4 types of diseases : liver cyst, hepatoma, cavernous hemagioma and metastatic liver tumor. Experimental results indicate that among these test data 78% of them are accurately classified as one type, while the remaining 22% of data are classified as more than one types of diseases. Even so, within theses 22% of multiple-classified data, the correct type is always included in the output in each test, showing a promise of the system.