Characterization of liver Disease Based on Ultrasound Imaging System
Mohammed K. Bin jaah1, Abdullah Aljuhani2, Umar S. Alqasemi3
1Mohammed K. Binjaah*, Department of Biomedical Engineering, King Abdul-Aziz University, KSA.
2Abdullah Aljuhani, Biomedical Engineer, Ministry of Health, KSA and Studying MSc Electrical and Biomedical Engineering, King Abdulaziz University, KSA.
3Umar Alqasemi, Associate Professor, Department of Electrical and Computer Engineering, King Abdulaziz University, KSA
Manuscript received on January 15, 2021. | Revised Manuscript received on February 02, 2021. | Manuscript published on February 28, 2021. | PP: 95-98 | Volume-10 Issue-3, February 2021. | Retrieval Number: 100.1/ijeat.C21670210321 | DOI: 10.35940/ijeat.C2167.0210321
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Computer-Aided Detection (CAD) systems are one of the most effected tools nowadays in aiding physicians in the detection of liver tumors at early stage. In this paper, the CADe system will be built which has the ability to detect the abnormal tumor inside the liver. In order to create that system, different types of classifiers must be implemented. In our CADe system, a support vector machine (SVM) and K-Nearest Neighbor (KNN) will be used as classifiers. A total number of 120 images including the normal and abnormal cases were collected. Initially, the features will be extracted from database images in order to distinguish between the classes of those liver tumors. Then, by using SVM and KNN the images will be classified into two classes normal and abnormal cases. The paper reveals that SVM and KNN, which demonstrated 100 percent precision, 100 percent sensitivity, and 100 percent specificity, were the best classifiers.
Keywords: Computer aided detection system, Liver cancer, Classification, SVM, KNN.
Scope of the Article: Classification