A Content-Based Medical Image Retrieval Method Using Relative Difference-Based Similarity Measure

作     者：Ali Ahmed Alaa Omran Almagrabi Omar MBarukab 

作者机构：Department of Computer ScienceFaculty of Computing and Information TechnologyKing Abdulaziz University–RabighRabigh21589Saudi Arabia Department of Information SystemsFaculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information TechnologyFaculty of Computing and Information TechnologyKing Abdulaziz University-RabighRabigh21589Saudi Arabia 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第37卷第8期

页      面：2355-2370页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：funded by the Deanship of Scientific Research (DSR)at King Abdulaziz University Jeddah Saudi Arabia Under Grant No. (G:146-830-1441) 

主　　题：Medical image retrieval feature extraction similarity measure fusion method 

摘      要：Content-based medical image retrieval(CBMIR)is a technique for retrieving medical images based on automatically derived image *** are many applications of CBMIR,such as teaching,research,diagnosis and electronic patient *** methods are applied to enhance the retrieval performance of CBMIR *** new and effective similarity measure and features fusion methods are two of the most powerful and effective strategies for improving these *** study proposes the relative difference-based similarity measure(RDBSM)for *** new measure was first used in the similarity calculation stage for the CBMIR using an unweighted fusion method of traditional color and texture ***,the study also proposes a weighted fusion method for medical image features extracted using pre-trained convolutional neural networks(CNNs)*** proposed RDBSM has outperformed the standard well-known similarity and distance measures using two popular medical image datasets,Kvasir and PH2,in terms of recall and precision retrieval *** effectiveness and quality of our proposed similarity measure are also proved using a significant test and statistical confidence bound.