[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-338464-105":59,"doc-detail-338464-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","multi-classification-of-breast-cancer-pathology-images-based-on-a-two-stage-hybrid-network-research","Multi-classification of breast cancer pathology images based on a two-stage hybrid network - Research","","Pathological image diagnosis serves as the clinical gold standard for cancer detection, yet breast lesions often require additional subtype classification after malignancy is determined. This study develops a multi-classification model for breast cancer pathology images using a two-stage hybrid network. A transfer-learned ResNet34 forms the first-level convolutional backbone, while an LSTM-based second-level component captures contextual long-range dependencies for improved subtype prediction.",{"@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":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/multi-classification-of-breast-cancer-pathology-images-based-on-a-two-stage-hybrid-network-research/338464/",{"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/multi-classification-of-breast-cancer-pathology-images-based-on-a-two-stage-hybrid-network-research/338464.png","ImageObject",300,407,{"name":92,"@type":93},"Seraphina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main objective of the two-stage hybrid network model?","Question",{"text":112,"@type":113},"To perform multi-classification of breast cancer pathology images, providing subtype predictions beyond the malignant/benign decision.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the model handle limited subtype sample size?",{"text":117,"@type":113},"It uses transfer learning with ResNet34 as the first-level convolutional network to support training under limited data conditions.",{"name":119,"@type":110,"acceptedAnswer":120},"What are the reported performance results on BreakHis and ICIAR2018 datasets?",{"text":121,"@type":113},"On BreakHis, the ensemble model achieves accuracy rates of 93.67%, 97.08%, 98.01%, and 94.73% for the 8 sub-types. On ICIAR2018, it reports accuracy, precision, recall, and F1 scores of 93.75%, 92.5%, 92.5%, and 92.5% for the 4 sub-types.","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},338464,1790362626,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"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,"preview_page_count":19,"preview_urls":146},962075114101,"https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165","Journal of Cancer Research and Clinical Oncology (2024) 150:505  \n[https://doi.org/10.1007/s00432-024-06002-y](https://doi.org/10.1007/s00432-024-06002-y)  \nRESEARCH  \nMulti-classification of breast cancer pathology images based on a twostage hybrid network  \nGuolan Wang1 · Mengjiu Jia1 · Qichao Zhou2 · Songrui Xu2 · Yadong Zhao2 · QiaorongWang2 · Zhi Tian3 · Ruyi Shi4 · Keke Wang5 · Ting Yan2 · Guohui Chen2 · Bin Wang6  \nReceived: 17 June 2024 / Accepted: 15 October 2024 / Published online: 18 November 2024 © The Author(s) 2024  \nAbstract  \nBackground and objective In current clinical medicine, pathological image diagnosis is the gold standard for cancer diagnosis. After pathologists determine whether breast lesions are malignant or benign, further sub-type classification is often necessary.  \nMethods For this task, this study designed a multi-classification model for breast cancer pathological images based on a two-stage hybrid network. Due to limited sample size for breast sub-type data, this study selected the ResNet34 network asthe base network and improved it as the first-level convolutional network, using transfer learning to assist network training. In order to compensate for the lack of long-distance dependencies in the convolutional network, the second-level network was designed to use Long Short-Term Memory (LSTM) to capture contextual information in the images for predictive classification.  \nResults For the 8 sub-types of breast cancer classification on the BreakHis (40×, 100×, 200×, 400×) dataset, the ensemble model achieved accuracy rates of 93.67%, 97.08%, 98.01%, and 94.73% respectively. For the 4 sub-types of breast cancer classification on the ICIAR2018 (200×) dataset, the ensemble model achieved accuracy, precision, recall, and F1 Score rates of 93.75%, 92.5%, 92.5%, and 92.5% respectively.  \nConclusion The results show that the multi-classification model proposed in this study outperforms other methods in terms of classification performance, and further demonstrate that the proposed RFSAM module is beneficial for improving model performance.  \nKeywords Pathological images of breast cancer · Two-stage hybrid network · Multi-classification  \nAbbreviations  \nLSTM Long Short-Term Memory  \nSum Probability summation  \nMaj Majority voting  \nMax Maximum probability  \nBin Wang and Guohui Chen contributed equally to this work.  \n􀀍 Guohui Chen [15343590882@163.com](15343590882@163.com)  \n􀀍 Bin Wang [wangbin01@tyut.edu.cn](wangbin01@tyut.edu.cn)  \n1 School of Computer Information Engineering, Shanxi Technology and Business University, Taiyuan, China  \n2 Translational Medicine Research Center, Shanxi Medical University, Taiyuan, Shanxi, People’s Republic of China  \nPC Papillary carcinoma  \nMC Mucinous carcinoma  \nB Benign tumors  \nN Normal  \n3FC Three fully connected layers  \n3 Second Clinical Medical College, Shanxi Medical University, 382 Wuyi Road, Taiyuan, Shanxi, People’s Republic of China  \n4 Department of Cell Biology and Genetics, Shanxi Medical University, Taiyuan, Shanxi, People’s Republic of China  \n5 The First Hospital of Shanxi Medical University, Taiyuan 030001, China  \n6 College of Information and Computer, Taiyuan University of Technology, Taiyuan, Shanxi, People’s Republic of China  \nFC Fully connected layers  \nRFSAM Receptive Field Scale Attention Module  \nIntroduction  \nCancer is currently one of the leading causes of human disease and death in the world. According to The World Health Organization’s 2020 global cancer statistics report, breast cancer has replaced lung cancer as the world’s largest cancer, seriously endangering the health and lives of women around the world (Sung et al. 2021) . In clinical medicine, pathological image diagnosis is the gold standard for cancer diagnosis (Swathi et al. 2019). However, due to the complex structure of pathological images, professional pathologists are required to carry out intensive work, which is time-consuming, labor-intensive, and inefficient. In addit","cbCaivyEWGUfNj5w","https://ap.wps.com/l/cbCaivyEWGUfNj5w","pdf",1770642,15,"English","# Abstract\n## Background and objective\n## Methods\n## Results\n## Conclusion\n# Introduction","[{\"question\":\"What is the main objective of the two-stage hybrid network model?\",\"answer\":\"To perform multi-classification of breast cancer pathology images, providing subtype predictions beyond the malignant/benign decision.\"},{\"question\":\"How does the model handle limited subtype sample size?\",\"answer\":\"It uses transfer learning with ResNet34 as the first-level convolutional network to support training under limited data conditions.\"},{\"question\":\"What are the reported performance results on BreakHis and ICIAR2018 datasets?\",\"answer\":\"On BreakHis, the ensemble model achieves accuracy rates of 93.67%, 97.08%, 98.01%, and 94.73% for the 8 sub-types. On ICIAR2018, it reports accuracy, precision, recall, and F1 scores of 93.75%, 92.5%, 92.5%, and 92.5% for the 4 sub-types.\"}]","Multi-classification of breast cancer pathology images based on a two-stage hybrid network - Research | PDF",1790023730,38,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c352ae28d30d702d9d81c7aa036985d1.webp",983,1305,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/edad5493de79520e6d4dd2bc05e21284.webp",982,1304,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5321762385cf71afc0df3c0005eb29d9.webp",981,1303,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/610335914eb2188a7331bbc50320df48.webp",980,1301]