Deep learning based detection of monkeypox virus using skin lesion images

作     者：Tushar Nayak Krishnaraj Chadaga Niranjana Sampathila Hilda Mayrose Nitila Gokulkrishnan Muralidhar Bairy G Srikanth Prabhu Swathi K.S Shashikiran Umakanth 

作者机构：Department of Biomedical EngineeringManipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka576104India Department of Computer Science and EngineeringManipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka576104India Prasanna School of Public HealthManipal Academy of Higher EducationManipalKarnataka576104India Department of MedicineDr.T.M.A.Pai HospitalManipal Academy of Higher EducationUdupiKarnataka576101India 

出 版 物：《Medicine in Novel Technology and Devices》 (医学中新技术与新装备（英文）)

年 卷 期：2023年第18卷第2期

页      面：234-246页

学科分类：1002[医学-临床医学] 100206[医学-皮肤病与性病学] 10[医学] 

基　　金：Manipal Academy of Higher Education  MAHE 

主　　题：Deep learning Disease diagnosis Image processing Monkeypox virus Machine learning Transfer learning 

摘      要：As we set into the second half of 2022,the world is still recovering from the two-year COVID-19 ***,over the past three months,the outbreak of the Monkeypox Virus(MPV)has led to fifty-two thousand confirmed cases and over one hundred *** caused the World Health Organisation to declare the outbreak a Public Health Emergency of International Concern(PHEIC).If this outbreak worsens,we could be looking at the Monkeypox virus causing the next global *** Monkeypox affects the human skin,the symptoms can be captured with regular *** samples of these images can be used as a training dataset for machine learning-based detection *** a regular camera to capture the skin image of the infected person and running it against computer vision models is *** this research,we use deep learning to diagnose monkeypox from skin lesion *** a publicly available dataset,we tested the dataset on five pre-trained deep neural networks:GoogLeNet,Places365-GoogLeNet,SqueezeNet,AlexNet and *** was done to choose the best *** metrics such as accuracy,precision,recall,f1-score and AUC were *** the above models,ResNet18 was able to obtain the highest accuracy of 99.49%.The modified models obtained validation accuracies above 95%.The results prove that deep learning models such as the proposed model based on ResNet-18 can be deployed and can be crucial in battling the monkeypox *** the used networks are optimized for efficiency,they can be used on performance limited devices such as smartphones with *** addition of explainable artificial intelligence techniques LIME and GradCAM enables visual interpretation of the prediction made,helping health professionals using the model.