[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-368969-105":59,"doc-detail-368969-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","non-small-cell-lung-cancer-subtype-classification-based-on-cross-scale-multi-instance-learning","Non-small cell lung cancer subtype classification based on cross-scale multi-instance learning","","Non-small cell lung cancer subtype identification for LUAD and LUSC remains difficult, impacting treatment planning. A multi-instance learning pathological image framework is presented with an additive attention mechanism and a new category classifier to improve subtype discrimination. The approach adds cross-scale focal region detection and a coarse-to-fine paradigm that mimics pathologists’ workflow, extracting global context and fine-grained morphology while promoting cross-magnification consistency. Training on TCGA achieves 97.0% ACC and 0.978 AUC, and external validation on CPTAC-TCIA and an additional hospital dataset reports strong robustness with high ACC and AUC.",{"@graph":69,"@context":123},[70,84,106],{"@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/non-small-cell-lung-cancer-subtype-classification-based-on-cross-scale-multi-instance-learning/368969/",{"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/non-small-cell-lung-cancer-subtype-classification-based-on-cross-scale-multi-instance-learning/368969.png","ImageObject",300,407,{"name":92,"@type":93},"PakDamar76","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-19","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What model framework is proposed for NSCLC subtype classification?","Question",{"text":113,"@type":114},"The study proposes a novel multi-instance learning framework that uses an additive attention mechanism and a category-specific classifier, combined with cross-scale focal region detection to improve discrimination between LUAD and LUSC.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the method use cross-scale information during inference?",{"text":118,"@type":114},"It follows a coarse-to-fine strategy: global assessment on low-magnification slides identifies candidate ROIs, which are then examined at higher magnification to extract fine-grained morphological features.",{"name":120,"@type":111,"acceptedAnswer":121},"How well does the model perform on internal and external datasets?",{"text":122,"@type":114},"On TCGA, the model achieves 97.0% ACC and 0.978 AUC. Generalization tests on CPTAC-TCIA (TCIA Lung) and an external Yantai Yuhuangding Hospital dataset report ACCs of 91.2% and 93.0% and AUCs of 0.967 and 0.968, respectively.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},368969,1790232034,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},962090893057,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nNon-small cell lung cancer subtype classification based on cross-scale multi-instance learning  \nPeihe Jiang1, Weilong Chen1, Guibin Zheng2􀀍, Xinna Li3􀀍 & Xiaogang Song4􀀍  \nLung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), the two major subtypes of non-small cell lung cancer (NSCLC), present significant diagnostic challenges with direct implications for treatment planning. In this study, we propose a novel multi-instance learning (MIL) pathological image classification model that incorporates an additive attention mechanism and a new category classifier to enhance subtype discrimination. The model further integrates a cross-scale focal region detection strategy to improve sensitivity to key histological features. Trained on the Cancer Genome Atlas (TCGA) dataset, our model achieved a subtype classification accuracy (ACC) of 97.0% and an area under the ROC curve (AUC) of 0.978, outperforming state-of-the-art methods including ABMIL, CLAM, DS-MIL, DTFD-MIL, FR-MIL, and WIKG-MIL across multiple evaluation metrics. Ablation studies validate the contribution of each module to overall performance improvement. Generalization experiments conducted on the Clinical Proteomic Tumor Analysis Consortium (CPTAC) Cancer Imaging Archive (TCIA) Lung dataset and an external dataset from Yantai Yuhuangding Hospital demonstrate the robustness of our model, achieving ACCs of 91.2% and 93.0%, andAUCs of 0.967 and 0.968, respectively. These results underscore the model’s strong generalization ability and its potential as a reliable tool for accurate NSCLC subtype classification across diverse clinical scenarios.  \nKeywords Multi-instance learning, Non-small cell lung cancer, Multi-scale, Pathology  \nLung cancer remains the leading cause of cancer-related mortality globally, with an estimated 1.8 million deaths (18.7% of all cancer deaths) reported in 2022, according to the International Agency for Research on Cancer (IARC)1. Among all lung cancers, approximately 80–85% are classified as non-small cell lung cancer (NSCLC), which includes two major histological subtypes: lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC). Accurate identification of these subtypes is crucial for determining treatment strategies2. With the advancement of Whole Slide Image (WSI) technology, histopathological analysis has entered the digital era3. Deep learning models applied to WSIs have demonstrated great promise in automating subtype classification. However, most of these approaches require exhaustive pixel-or tile-level annotations, which are time-consuming and heavily dependent on expert pathologists4. To alleviate this burden, weakly supervised learning strategies, particularly multi-instance learning (MIL), have been introduced. MIL leverages slide-level labels to infer instance-level (tile-level) features, enabling more scalable and annotation-efficient model training.  \nDespite their promise, existing MIL approaches often exhibit two key limitations: (1) limited capacity to capture nuanced morphological differences between LUAD and LUSC, and (2) inadequate integration of multi-scale contextual information, which is vital for accurate diagnosis.  \nTo overcome these challenges, we propose a novel MIL-based framework that mimics the diagnostic workflow of pathologists through a coarse-to-fine, cross-scale analysis paradigm. Specifically, the model first conducts a global assessment of low-magnification WSIs to identify candidate regions of interest (ROIs), simulating the initial screening phase in routine pathology. These regions are subsequently examined at higher magnification to extract fine-grained morphological features, thereby emulating the pathologist’s zoom-in process for detailed inspection. Furthermore, we introduce an additive attention mechanism and a category-specific classifier to improve the model’s capacity for subtype discrimination. To","cbCaifO7yA2zOwEK","https://ap.wps.com/l/cbCaifO7yA2zOwEK","pdf",5330687,13,"English","# Introduction\n## Clinical challenge of NSCLC subtype classification\n## Weakly supervised learning and MIL motivation\n## Key limitations of existing MIL methods\n# Proposed Method\n## Coarse-to-fine cross-scale framework\n## Additive attention and category-specific classification\n## Tagging and prompting for cross-scale consistency\n# Contributions","[{\"question\":\"What model framework is proposed for NSCLC subtype classification?\",\"answer\":\"The study proposes a novel multi-instance learning framework that uses an additive attention mechanism and a category-specific classifier, combined with cross-scale focal region detection to improve discrimination between LUAD and LUSC.\"},{\"question\":\"How does the method use cross-scale information during inference?\",\"answer\":\"It follows a coarse-to-fine strategy: global assessment on low-magnification slides identifies candidate ROIs, which are then examined at higher magnification to extract fine-grained morphological features.\"},{\"question\":\"How well does the model perform on internal and external datasets?\",\"answer\":\"On TCGA, the model achieves 97.0% ACC and 0.978 AUC. Generalization tests on CPTAC-TCIA (TCIA Lung) and an external Yantai Yuhuangding Hospital dataset report ACCs of 91.2% and 93.0% and AUCs of 0.967 and 0.968, respectively.\"}]","Non-small cell lung cancer subtype classification based on cross-scale multi-instance learning | PDF",1790179953,33,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fdf9ce1bbc9f85f20c1fc423a562b3ea.webp",983,1291,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/51c82243099973f6d396a9c36d319e09.webp",982,1290,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/62bf7483e3770479896557585102edce.webp",981,1289,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/56f9f47f09cbebdb7ab1265ee4c85f78.webp",980,1287]