[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-371294-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-371294-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","auxiliary-meta-learning-strategy-for-cancer-recognition-leveraging-external-data-and-optimized-feature-mapping","Auxiliary meta-learning strategy for cancer recognition - leveraging external data and optimized feature mapping","","As reported by the International Agency for Research on Cancer (IARC), cancer incidence approaches 20 million new cases annually, with about 9.7 million deaths, highlighting a major global public health burden. Deep learning is effective for cancer recognition but typically requires large labeled datasets. Few-shot learning reduces labeling demand; however, cancer data are scarce across categories and existing methods still underperform. This work proposes an auxiliary meta-learning strategy that uses external data in auxiliary training, optimizes embedding-space learning with prototypes and cosine distance, and evaluates via extensive experiments on BreakHis, Pap smear, and ISIC 2018.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/auxiliary-meta-learning-strategy-for-cancer-recognition-leveraging-external-data-and-optimized-feature-mapping/371294/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/auxiliary-meta-learning-strategy-for-cancer-recognition-leveraging-external-data-and-optimized-feature-mapping/371294.png","ImageObject",300,407,{"name":42,"@type":43},"Oliver","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-06","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",15,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is few-shot learning important for cancer recognition?","Question",{"text":63,"@type":64},"Cancer categories are often rare, making labeled data difficult to collect. Few-shot learning reduces the need for extensive labeled samples while aiming to maintain recognition performance.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the proposed method use external data during training?",{"text":68,"@type":64},"During auxiliary training, a feature mapping model is trained together with external data so misclassification prediction probabilities are neutralized. This helps the model learn distinguishing features and reduces performance degradation from external data discrepancies.",{"name":70,"@type":61,"acceptedAnswer":71},"How is classification performed in the meta-testing stage?",{"text":72,"@type":64},"In meta-testing, a small number of labeled samples are used to classify unknown data, leveraging the learned embedding-space optimization from meta-training.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},371294,1790457639,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":33,"preview_urls":147},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Wang et al. BMC Cancer (2025) 25:367 [https://doi.org/10.1186/s12885-025-13740-w](https://doi.org/10.1186/s12885-025-13740-w)  \nBMC Cancer  \n RESEARCH Open Access  \nAuxiliary meta-learning strategy for cancer recognition: leveraging external data and optimized feature mapping  \nKang Wang1,2, Xihong Fei1,2, Lei Su1,2, Tian Fang1,2 and Hao Shen1,2*  \nAbstract  \nAs reported by the International Agency for Research on Cancer (IARC), the global incidence of cancer reached nearly 20 million new cases in recent years, with cancer-related fatalities amounting to around 9.7 million. This underscores the profound impact cancer has on public health worldwide. Deep learning has become a mainstream approach in cancer recognition. Despite its significant progress, deep learning is known for its requirement of large quantities of labeled data. Few-shot learning addresses this limitation by reducing the need for extensive labeled samples. In the field of cancer recognition, data collection is particularly challenging due to the scarcity of categories compared to other fields, and current few-shot learning methods have not yielded satisfactory results. To tackle this, we propose an auxiliary meta-learning strategy for cancer recognition. During the auxiliary training phase, the feature mapping model is trained in conjunction with external data. This process neutralizes the prediction probability of misclassification, allowing the model to more readily learn distinguishing features and avoid performance degradation caused by discrepancies in external data. Additionally, the redundancy of some input principal components in the feature mapping model is reduced, while the implicit information within these components is extracted. The training process is further accelerated by utilizing depthwise over-parameterized convolutional layers. Moreover, the implementation of a three-branch structure contributes to faster training and enhanced performance. In the meta-training stage, the feature mapping model is optimized within the embedding space, utilizing category prototypes and cosine distance. During the meta-testing phase, a small number of labeled samples are employed to classify unknown data. We have conducted extensive experiments on the BreakHis, Pap smear, and ISIC 2018 datasets. The results demonstrate that our method achieves superior accuracy in cancer recognition. Furthermore, experiments on few-shot benchmark datasets indicate that our approach exhibits excellent generalization capabilities.  \nKeywords Few-shot learning, Meta-learning, Medical image classification, Cancer recognition  \n*Correspondence: Hao Shen [haoshen10@gmail.com](haoshen10@gmail.com)  \n1 Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes, Anhui University of Technology, Ma’anshan 243032, Anhui, China  \n2 School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan 243032, Anhui, China  \nIntroduction  \nCancer, a fatal disease caused by a variety of biochemical abnormalities and genetic disorders, has become oneof the leading causes of disability and death in humans, posing a great challenge to scientists and researchers [1–3]. Detecting cancer at an early stage enables patients to receive appropriate treatment and increases the chances of survival. Deep learning [4, 5] methods have been widely used to accelerate the identification of cancers, enabling more patients to be examined in a shorter  \n© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share ada","cbCaiccKEw1jlRsv","https://ap.wps.com/l/cbCaiccKEw1jlRsv","pdf",4293082,17,"English","# Abstract\n# Introduction\n## Motivation: cancer burden and labeled-data scarcity\n## Need for few-shot cancer recognition\n# Methods overview\n## Auxiliary training with external data and optimized feature mapping\n## Meta-training with prototypes and cosine distance\n## Meta-testing with limited labeled samples\n# Experiments and results\n## BreakHis, Pap smear, ISIC 2018\n## Few-shot benchmark generalization","[{\"question\":\"Why is few-shot learning important for cancer recognition?\",\"answer\":\"Cancer categories are often rare, making labeled data difficult to collect. Few-shot learning reduces the need for extensive labeled samples while aiming to maintain recognition performance.\"},{\"question\":\"How does the proposed method use external data during training?\",\"answer\":\"During auxiliary training, a feature mapping model is trained together with external data so misclassification prediction probabilities are neutralized. This helps the model learn distinguishing features and reduces performance degradation from external data discrepancies.\"},{\"question\":\"How is classification performed in the meta-testing stage?\",\"answer\":\"In meta-testing, a small number of labeled samples are used to classify unknown data, leveraging the learned embedding-space optimization from meta-training.\"}]","Auxiliary meta-learning strategy for cancer recognition - leveraging external data and optimized feature mapping | PDF",1790191724,43,[148,152,156,160],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9a36d1563b29b13dcb7f117f60d66336.webp",983,1305,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4102f82c44183f5cef5b3540ffaab262.webp",982,1304,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3c798623850330efff7a5c2b80afc122.webp",981,1303,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/631479c81868f01698d36f3eba0c6e0e.webp",980,1301]