Arithmetic Optimization with Ensemble Deep Transfer Learning Based Melanoma Classification  

作　　者：K.Kalyani Sara A Althubiti Mohammed Altaf Ahmed ELaxmi Lydia Seifedine Kadry Neunggyu Han Yunyoung Nam 

机构地区：[1]Department of Computer Science,Dr.Nalli Kuppusamy Arts College(Affiliated to Bharathidasan University,Tiruchirappalli),Thanjavur,613003,India [2]Department of Computer Science,College of Computer and Information Sciences,Majmaah University,Al-Majmaah,11952,Saudi Arabia [3]Lepartment of Computer Engineering,College of Computer Engineering&Sciences,Prince Sattam Bin Abdulaziz University,Al-Kharj,11942,Saudi Arabia [4]Department of Computer Science and Engineering,Vignan’s Institute of Information Technology,Visakhapatnam,530049,India [5]Department of Applied Data Science,Noroff University College,Kristiansand,Norway [6]Department of ICT Convergence,Soonchunhyang University,Korea

出　　处：《Computers, Materials & Continua》2023年第4期149-164,共16页计算机、材料和连续体（英文）

基　　金：supported by the MSIT (Ministry of Science and ICT),Korea,under the ICAN (ICT Challenge and Advanced Network of HRD)program (IITP-2022-2020-0-01832)supervised by the IITP (Institute of Information&Communications Technology Planning&Evaluation)and the Soonchunhyang University Research Fund.

摘　　要：Melanoma is a skin disease with high mortality rate while earlydiagnoses of the disease can increase the survival chances of patients. Itis challenging to automatically diagnose melanoma from dermoscopic skinsamples. Computer-Aided Diagnostic (CAD) tool saves time and effort indiagnosing melanoma compared to existing medical approaches. In this background,there is a need exists to design an automated classification modelfor melanoma that can utilize deep and rich feature datasets of an imagefor disease classification. The current study develops an Intelligent ArithmeticOptimization with Ensemble Deep Transfer Learning Based MelanomaClassification (IAOEDTT-MC) model. The proposed IAOEDTT-MC modelfocuses on identification and classification of melanoma from dermoscopicimages. To accomplish this, IAOEDTT-MC model applies image preprocessingat the initial stage in which Gabor Filtering (GF) technique is utilized.In addition, U-Net segmentation approach is employed to segment the lesionregions in dermoscopic images. Besides, an ensemble of DL models includingResNet50 and ElasticNet models is applied in this study. Moreover, AOalgorithm with Gated Recurrent Unit (GRU) method is utilized for identificationand classification of melanoma. The proposed IAOEDTT-MC methodwas experimentally validated with the help of benchmark datasets and theproposed model attained maximum accuracy of 92.09% on ISIC 2017 dataset.

关 键 词：Skin cancer deep learning melanoma classification DERMOSCOPY computer aided diagnosis 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]