[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127047-en":3,"doc-seo-127047-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127047,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",7,"Healthcare","Diagnosis of Multiple Fundus Disorders Amidst a Scarcity of Medical Experts Via Self-supervised Machine Learning","Fundus diseases drive major visual impairment and blindness worldwide, with the burden most severe in underdeveloped regions where ophthalmologists are scarce and timely diagnosis is delayed. Current AI fundus screening methods often depend on large amounts of expert-annotated data, limiting scalability and introducing labeling inconsistency. A general self-supervised machine learning framework is proposed to learn from unlabeled fundus images, improving accessibility and enabling label-free diagnosis across diverse datasets, races, and heterogeneous imaging sources.","IEEE TRANSACTIONS AND JOURNALS TEMPLATE  \n1  \nThis work was supported in part by the National Natural Science Foundation under Grant 62171014 , National Natural Science Foundation of China 82201244 , Natural Science Foundation of Beijing M22019 , Beijing Hospitals Authority Innovation Studio of Young Staff Funding Support 202106 and from the UKRI EPSRC, under grants EP/K03099X/ 1 , EP/S023283/1. Corresponding authors: Shuo Gao ([shuo_gao@buaa.edu.cn](shuo_gao@buaa.edu.cn)) and Luigi G. Occhipinti ([lgo23@cam.ac.uk](lgo23@cam.ac.uk)).  \nYong Liu and Mengtian Kang contributed equally to this work.  \nYong Liu is with the School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China. (e-mail: [yongliu@buaa.edu.cn](yongliu@buaa.edu.cn)) .  \nMengtian Kang was with Beijing Tongren Hospital, Capital Medical University, Beijing, China (e-mail: [kangmengtian@163.com](kangmengtian@163.com)) .  \nShuo Gao is with the School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China. (e-mail: [shuo_gao@buaa.edu.cn](shuo_gao@buaa.edu.cn)) .  \nChi Zhang is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. (e-mail: [czhang0426@163.com](czhang0426@163.com))  \nYing Liu is with the Department of Surgery (Ophthalmology) , The University of Melbourne, Melbourne, Australia. (e-mail: [448689563@qq.com](448689563@qq.com))  \nShiming Li is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. (e-mail: [lishiming81@163.com](lishiming81@163.com))  \nYue Qi is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. (e-mail: [qiyue@126.com](qiyue@126.com))  \nArokia Nathan is with Darwin College, University of Cambridge, Cambridge, UK. (e-mail: [an299@cam.ac.uk](an299@cam.ac.uk))  \nWenjun Xu is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. (e-mail: [sallyxuwenjun@163.com](sallyxuwenjun@163.com))  \nChenyu Tang is with the Department of Engineering, University of Cambridge, Cambridge, UK. (e-mail: [ct631@cam.ac.uk](ct631@cam.ac.uk))  \nEdoardo Occhipinti is with the Department of Computing, Imperial College London, UKRI Centre for Doctoral Training in AI for Health, London, UK. (e-mail: [edoardo.occhipinti16@imperial.ac.uk](edoardo.occhipinti16@imperial.ac.uk))  \nMayinuer Yusufu is with the Department of Surgery (Ophthalmology) , The University of Melbourne, Melbourne, Australia.([e-mail: mayinuer.yusufu@student.unimelb.edu.au](e-mail: mayinuer.yusufu@student.unimelb.edu.au))  \nNingli Wang is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. ([e-mail: wningli@vip.163.com](e-mail: wningli@vip.163.com))  \nWeiling Bai is with Beijing Tongren Hospital, Capital Medical University, Beijing, China. (e-mail: [15811025078@163.com](15811025078@163.com))  \nLuigi Occhipinti is with the Department of Engineering, University of Cambridge, Cambridge, UK. (e-mail: [lgo23@cam.ac.uk](lgo23@cam.ac.uk))  \nDiagnosis of Multiple Fund us Disorders Amidst a Scarcity of Medical Experts Via Self-supervised  \nMachine Learning  \nYong Liu, Mengtian Kang, Shuo Gao, Chi Zhang, Ying Liu, Shiming Li, Yue Qi, Arokia Nathan, Wenjun Xu, Chenyu Tang, Edoardo Occhipinti, Mayinuer Yusufu, Ningli Wang, Weiling Bai, and Luigi Occhipinti  \nAbstract— Fundus diseases are major causes of visual impairment and blindness worldwide, especially in underdeveloped regions, where the shortage of ophthalmologists hinders timely diagnosis. AI-assisted fundus image analysis has several advantages, such as high accuracy, reduced workload, and improved accessibility, but it requires a large amount of expertannotated data to build reliable models. To address this dilemma, we propose a general self-supervised machine learning framework that can handle diverse fundus diseases from unlabeled fundus images. Our method’s AUC surpasses existing supervised approaches by 15.7%, and even exceeds performance of a single human expert. Furthermore, our mode","cbCaip3FDQ1K3mnL","https://ap.wps.com/l/cbCaip3FDQ1K3mnL","pdf",2880913,2,1,12,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"Why is diagnosis of fundus diseases difficult in many regions?\",\"answer\":\"Many regions face a severe shortage of ophthalmologists, making timely diagnosis difficult. Limited expert availability also restricts large-scale model development.\"},{\"question\":\"What problem does the proposed approach address?\",\"answer\":\"It addresses the reliance on expert-annotated fundus data by using a general self-supervised framework that trains from unlabeled images.\"},{\"question\":\"How does the method perform compared with supervised approaches?\",\"answer\":\"The method’s AUC surpasses existing supervised approaches by 15.7% and can even exceed the performance of a single human expert.\"}]","Diagnosis of Multiple Fundus Disorders Amidst a Scarcity of Medical Experts Via Self-supervised Machine Learning | PDF",1785936535,30,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"diagnosis-of-multiple-fundus-disorders-amidst-a-scarcity-of-medical-experts-via-self-supervised-machine-learning","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/diagnosis-of-multiple-fundus-disorders-amidst-a-scarcity-of-medical-experts-via-self-supervised-machine-learning/127047/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is diagnosis of fundus diseases difficult in many regions?","Question",{"text":76,"@type":77},"Many regions face a severe shortage of ophthalmologists, making timely diagnosis difficult. Limited expert availability also restricts large-scale model development.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What problem does the proposed approach address?",{"text":81,"@type":77},"It addresses the reliance on expert-annotated fundus data by using a general self-supervised framework that trains from unlabeled images.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the method perform compared with supervised approaches?",{"text":85,"@type":77},"The method’s AUC surpasses existing supervised approaches by 15.7% and can even exceed the performance of a single human expert.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,119,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":117,"slug":118},40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":30,"slug":122},8,"Research & Report","research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]