A New Method for Diagnosis of Leukemia Utilizing a Hybrid DL-ML Approach for Binary and Multi-Class Classification on a Limited-Sized Database

作     者：Nilkanth Mukund Deshpande Shilpa Gite Biswajeet Pradhan Abdullah Alamri Chang-Wook Lee 

作者机构：Department of Electronics&TelecommunicationLavaleSymbiosis Institute of TechnologySymbiosis International(Deemed University)PuneMaharashtra412115India Electronics&TelecommunicationDr.Vithalrao Vikhe Patil College of EngineeringAhmednagarMaharashtra414111India Artificial Intelligence and Machine Learning DepartmentSymbiosis Institute of TechnologySymbiosis International(Deemed)UniversityPune412115India Symbiosis Centre of Applied AI(SCAAI)Symbiosis International(Deemed)UniversityPune412115India Centre for AdvancedModelling and Geospatial Information Systems(CAMGIS)School of Civil and Environmental EngineeringFaculty of Engineering&ITUniversity of Technology SydneySydneyAustralia Earth Observation CentreInstitute of Climate ChangeUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia Department of Geology&GeophysicsCollege of ScienceKing Saud UniversityP.O.Box 2455Riyadh11451Saudi Arabia Department of Science EducationKangwon National UniversityChuncheon-si24341Korea 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2024年第139卷第4期

页      面：593-631页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 0701[理学-数学] 10[医学] 

基　　金：supported by the Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS),the University of Technology Sydney,the Ministry of Education of the Republic of Korea,and the National Research Foundation of Korea (NRF-2023R1A2C1007742) in part by the Researchers Supporting Project Number RSP-2023/14,King Saud University 

主　　题：Leukemia diagnosis deep learning machine learning random forest XGBoost 

摘      要：Infection of leukemia in humans causes many complications in its later *** impairs bone marrow’s ability to produce *** diagnosis of human blood cells is a well-known and well-proven technique for diagnosis in this *** binary classification is employed to distinguish between normal and leukemiainfected *** addition,various subtypes of leukemia require different *** sub-classes must also be detected to obtain an accurate diagnosis of the type of *** entails using multi-class classification to determine the leukemia *** is usually done using a microscopic examination of these blood *** to the requirement of a trained pathologist,the decision process is critical,which leads to the development of an automated software framework for *** utilized state-of-the-art machine learning approaches,such as Support Vector Machine(SVM),Random Forest(RF),Na飗e Bayes,K-Nearest Neighbor(KNN),and others,to provide limited accuracies of *** advanced deep-learning methods are also *** to constrained dataset sizes,these approaches result in over-fitting,reducing their outstanding *** study introduces a deep learning-machine learning combined approach for leukemia *** uses deep transfer learning frameworks to extract and classify features using state-of-the-artmachine learning *** transfer learning frameworks such as VGGNet,Xception,InceptionResV2,Densenet,and ResNet are employed as feature *** extracted features are given to RF and XGBoost classifiers for the binary and multi-class classification of leukemia *** the experimentation,a very popular ALL-IDB dataset is used,approaching a maximum accuracy of 100%.A private real images dataset with three subclasses of leukemia images,including Acute Myloid Leukemia(AML),Chronic Lymphocytic Leukemia(CLL),and Chronic Myloid Leukemia(CML),is also employed to generalize the *** d