Symbiotic Organisms Search with Deep Learning Driven Biomedical Osteosarcoma Detection and Classification

作     者：Abdullah M.Basahel Mohammad Yamin Sulafah M.Basahel Mona M.Abusurrah K.Vijaya Kumar E.Laxmi Lydia 

作者机构：Faculty of Economics and AdministrationKing Abdulaziz UniversityJeddahSaudi Arabia E-Commerce DepartmentCollege of Administrative and Financial SciencesSaudi Electronic UniversityJeddahSaudi Arabia Department of Management Information SystemsCollege of Business AdministrationTaibah UniversityAl-MadinahSaudi Arabia Department of Computer Science and EngineeringGITAM School of TechnologyVisakhapatnam CampusGITAM(Deemed to be a University)India Department of Computer Science and EngineeringGMR Institute of TechnologyAndhra PradeshRajamIndia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第75卷第4期

页      面：133-148页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The Deanship of Scientific Research (DSR)at King Abdulaziz University (KAU) Jeddah Saudi Arabia has funded this project under grant no KEP-1-120-42 

主　　题：Osteosarcoma medical imaging deep learning feature vectors computer aided diagnosis image classification 

摘      要：Osteosarcoma is one of the rare bone cancers that affect the individualsaged between 10 and 30 and it incurs high death rate. Early diagnosisof osteosarcoma is essential to improve the survivability rate and treatmentprotocols. Traditional physical examination procedure is not only a timeconsumingprocess, but it also primarily relies upon the expert’s *** this background, the recently developed Deep Learning (DL) models canbe applied to perform decision making. At the same time, hyperparameteroptimization of DL models also plays an important role in influencing overallclassification performance. The current study introduces a novel SymbioticOrganisms Search with Deep Learning-driven Osteosarcoma Detection andClassification (SOSDL-ODC) model. The presented SOSDL-ODC techniqueprimarily focuses on recognition and classification of osteosarcoma usinghistopathological images. In order to achieve this, the presented SOSDL-ODCtechnique initially applies image pre-processing approach to enhance the qualityof image. Also, MobileNetv2 model is applied to generate a suitable groupof feature vectors whereas hyperparameter tuning of MobileNetv2 modelis performed using SOS algorithm. At last, Gated Recurrent Unit (GRU)technique is applied as a classification model to determine proper class *** order to validate the enhanced osteosarcoma classification performance ofthe proposed SOSDL-ODC technique, a comprehensive comparative analysiswas conducted. The obtained outcomes confirmed the betterment of SOSDLODCapproach than the existing approaches as the former achieved a maximumaccuracy of 97.73%.