Liver Tumor Decision Support System on Human Magnetic Resonance Images:A Comparative Study

作     者：Hiam Alquran Yazan Al-Issa Mohammed Alslatie Isam Abu-Qasmieh Amin Alqudah Wan Azani Mustafa Yasmin Mohd Yacob 

作者机构：Department of Biomedical Systems and Informatics EngineeringYarmouk University 556Irbid21163Jordan Department of Biomedical EngineeringJordan University of Science and TechnologyIrbid22110Jordan Department of Computer EngineeringYarmouk University 556Irbid21163Jordan The of Biomedical TechnologyKing Hussein Medical CenterRoyal Jordanian Medical ServiceAmman11855Jordan Faculty of Electrical Engineering&TechnologyCampus Pauh PutraUniversiti Malaysia PerlisArau02600PerlisMalaysia Faculty of Electronic Engineering&TechnologyCampus Pauh PutraUniversiti Malaysia PerlisArau02600PerlisMalaysia Advanced ComputingCentre of Excellence(CoE)Universiti Malaysia PerlisArau02600PerlisMalaysia 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第46卷第8期

页      面：1653-1671页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

主　　题：Liver tumors ensemble classifier 3D shape features 3D cooccurrence matrix ResNet101 

摘      要：Liver cancer is the second leading cause of cancer death *** tumor detection may help identify suitable treatment and increase the survival *** imaging is a non-invasive tool that can help uncover abnormalities in human *** Resonance Imaging(MRI),in particular,uses magnetic fields and radio waves to differentiate internal human organs ***,the interpretation of medical images requires the subjective expertise of a radiologist and ***,building an automated diagnosis computer-based system can help specialists reduce incorrect *** paper proposes a hybrid automated system to compare the performance of 3D features and 2D features in classifying magnetic resonance liver tumor *** paper proposed two models;the first one employed the 3D features while the second exploited the 2D *** first system uses 3D texture attributes,3D shape features,and 3D graphical deep descriptors beside an ensemble classifier to differentiate between four 3D tumor *** top of that,the proposed method is applied to 2D slices for comparison *** proposed approach attained 100%accuracy in discriminating between all types of tumors,100%Area Under the Curve(AUC),100%sensitivity,and 100%specificity and precision as well in 3D liver *** the other hand,the performance is lower in 2D *** maximum accuracy reached 96.4%for two classes and 92.1%for four *** top-class performance of the proposed system can be attributed to the exploitation of various types of feature selection methods besides utilizing the ReliefF features selection technique to choose the most relevant features associated with different *** novelty of this work appeared in building a highly accurate system under specific circumstances without any processing for the images and human input,besides comparing the performance between 2D and 3D *** the future,the presented work can be extended to be