[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-377789-105":59,"doc-detail-377789-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","using-less-annotation-workload-to-establish-a-pathological-auxiliary-diagnosis-system-for-gastric-cancer","Using less annotation workload to establish a pathological auxiliary diagnosis system for gastric cancer","","Pathological diagnosis of gastric cancer demands extensive expertise, and heavy day-to-day slide review can reduce accuracy through fatigue and inter-expert variability. A deep learning–based pathological auxiliary diagnosis system is developed using 1,514 stomach H&E–stained cases with complete diagnostic information. At the slide level, it reaches 0.8878 specificity while sustaining sensitivity near 1.0 across biopsy and surgical cohorts, improves classified accuracy on external multi-center data, and reduces pathologists’ false-negative/false-positive rates, uncertainty rate, and diagnosis time.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/using-less-annotation-workload-to-establish-a-pathological-auxiliary-diagnosis-system-for-gastric-cancer/377789/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/using-less-annotation-workload-to-establish-a-pathological-auxiliary-diagnosis-system-for-gastric-cancer/377789.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-09-24",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the proposed system address in gastric cancer pathology?","Question",{"text":112,"@type":113},"It helps pathologists improve diagnostic accuracy and efficiency by reducing workload, fatigue-related errors, and variability across experts when reviewing H&E-stained slides.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the pathological auxiliary diagnosis system developed and validated?",{"text":117,"@type":113},"It was trained using 1,514 cases of stomach H&E–stained specimens with complete diagnostic information and evaluated with both internal and external validations.",{"name":119,"@type":110,"acceptedAnswer":120},"What performance improvements does the system provide at the slide level?",{"text":121,"@type":113},"The system achieves 0.8878 specificity while keeping sensitivity close to 1.0, and it improves classified accuracy on multi-center biopsy specimens.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},377789,1790386387,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Article  \nUsing less annotation workload to establish a pathological auxiliary diagnosis system for gastric cancer  \nAuthors  \nJunlin Lan, Musheng Chen, Jianchao Wang, ..., Xiaogen Zhou, Tong Tong, Gang Chen  \nCorrespondence  \n[ttraveltong@gmail.com](ttraveltong@gmail.com) (T.T.),  \n[naichengang@126.com](naichengang@126.com) (G.C.)  \nIn brief  \nLan et al. establish a pathological auxiliary diagnosis system for gastric cancer based on deep learning. The feasibility and benefits ofthe system have been demonstrated through internal and external validations. After using the system, pathologists obtain significant benefits for the diagnosis of biopsy specimens.  \nd A pathological auxiliary diagnosis system for gastric cancer is proposed  \nd Active learning is applied to reduce the annotation workload  \nd An interpretation method to improves the specificity at the slide level  \nd The system significantly helps with the diagnosis of biopsy specimens  \nLan et al., 2023, Cell Reports Medicine 4, 101004 April 18, 2023 ª 2023 The Author(s) .  \n[https://doi.org/10.1016/j.xcrm.2023.101004](https://doi.org/10.1016/j.xcrm.2023.101004)  \nll  \nll  \nOPEN ACCESS  \nArticle  \nUsing less annotation workload to establish a pathological  \nauxiliary diagnosis system for gastric cancer  \nJunlin Lan,1,2,7 Musheng Chen,3,4,7 Jianchao Wang,3,4 Min Du,1,2 Zhida Wu,3,4 Hejun Zhang,3,4 Yuyang Xue,6 Tao Wang,1,2 Lifan Chen,3,4 Chaohui Xu,1,2 Zixin Han,1,2 Ziwei Hu,1,2 Yuanbo Zhou,1,2 Xiaogen Zhou,1,2 Tong Tong,1,2,5,8,*  \nand Gang Chen3,4,*  \n1College of Physics and Information Engineering, Fuzhou University, Fuzhou, Fujian 350108, China  \n2Key Lab of Medical Instrumentation & Pharmaceutical Technology of Fujian Province, Fuzhou University, Fuzhou, Fujian 350108, China  \n3Department of Pathology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, Fujian 350014, China  \n4Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou, Fujian 350014, China  \n5Imperial Vision Technology, Fuzhou, Fujian 350100, China  \n6School of Engineering, University of Edinburgh, Edinburgh EH8 9JU, UK  \n7These authors contributed equally  \n8Lead contact  \n*Correspondence: [ttraveltong@gmail.com](ttraveltong@gmail.com) (T.T.), [naichengang@126.com](naichengang@126.com) (G.C.) [https://doi.org/10.1016/j.xcrm.2023.101004](https://doi.org/10.1016/j.xcrm.2023.101004)  \nSUMMARY  \nPathological diagnosis of gastric cancer requires pathologists to have extensive clinical experience. To help pathologists improve diagnostic accuracy and efficiency, we collected 1,514 cases of stomach H&E-stained specimens with complete diagnostic information to establish a pathological auxiliary diagnosis system based on deep learning. At the slide level, our system achieves a specificity of 0.8878 while maintaining a high sensitivity close to 1.0 on 269 biopsy specimens (147 malignancies) and 163 surgical specimens (80 malignancies) . The classified accuracy of our system is 0.9034 at the slide level for 352 biopsy specimens (201 malignancies) from 50 medical centers. With the help of our system, the pathologists’ average false-negative rate and average false-positive rate on 100 biopsy specimens (50 malignancies) are reduced to 1/5 and 1/2 of the original rates, respectively. Atthe sametime, the average uncertainty rate and the average diagnosis time are reduced by approximately 22% and 20%, respectively.  \nINTRODUCTION  \nGastric cancer is the fifth most common malignant tumor and the third most common cause of cancer-related death worldwide.1 The incidence remains high in China, accounting for about half of cases worldwide and resulting in an estimated 288,500 deaths in 2016 .2 In recent decades, a gradual decrease in incidence and mortality rates has been observed with the popularization of endoscopic screening, but the prognosis is still poor due to theasymptomatic manifestations or nonspecific symptoms at the early stage.3 Accurate histopathological diagnosis of endoscopic","cbCaiqVoW68WHbsl","https://ap.wps.com/l/cbCaiqVoW68WHbsl","pdf",6977451,18,"English","# Summary\n# Introduction\n## Clinical need for accurate gastric cancer pathology\n## Digital pathology and deep learning background","[{\"question\":\"What problem does the proposed system address in gastric cancer pathology?\",\"answer\":\"It helps pathologists improve diagnostic accuracy and efficiency by reducing workload, fatigue-related errors, and variability across experts when reviewing H\\u0026E-stained slides.\"},{\"question\":\"How was the pathological auxiliary diagnosis system developed and validated?\",\"answer\":\"It was trained using 1,514 cases of stomach H\\u0026E–stained specimens with complete diagnostic information and evaluated with both internal and external validations.\"},{\"question\":\"What performance improvements does the system provide at the slide level?\",\"answer\":\"The system achieves 0.8878 specificity while keeping sensitivity close to 1.0, and it improves classified accuracy on multi-center biopsy specimens.\"}]","Using less annotation workload to establish a pathological auxiliary diagnosis system for gastric cancer | PDF",1790227166,45]