[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-368274-105":59,"doc-detail-368274-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","improving-lung-cancer-pathological-hyperspectral-diagnosis-through-cell-level-annotation-refinement","Improving lung cancer pathological hyperspectral diagnosis through cell-level annotation refinement","","Improving lung cancer pathological hyperspectral diagnosis relies on accurate cell-level annotations to support deep learning training. The study develops a semi-automated annotation refinement workflow that addresses coarse manual labels by using hyperspectral spectral features. K-means unsupervised clustering is combined with human-guided selection to convert coarse regions into cell-level masks. Validation on a lung squamous cell carcinoma hyperspectral dataset with 65 samples shows pixel segmentation accuracy rising from 77.33% to 92.52% with reduced prediction noise, while labeling time drops to about 5 minutes per slide.",{"@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/improving-lung-cancer-pathological-hyperspectral-diagnosis-through-cell-level-annotation-refinement/368274/",{"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/improving-lung-cancer-pathological-hyperspectral-diagnosis-through-cell-level-annotation-refinement/368274.png","ImageObject",300,407,{"name":92,"@type":93},"Ezra","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are accurate annotations critical for hyperspectral lung cancer diagnosis?","Question",{"text":112,"@type":113},"Deep learning models for hyperspectral analysis require precise training labels. Coarse manual annotations can degrade model performance by limiting the quality of supervision.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What method does the study propose to refine coarse annotations?",{"text":117,"@type":113},"It proposes a semi-automated pipeline using K-means unsupervised clustering with human-guided selection, transforming coarse annotations into cell-level masks based on spectral features.",{"name":119,"@type":110,"acceptedAnswer":120},"How much does the approach improve segmentation accuracy and labeling time?",{"text":121,"@type":113},"On a hyperspectral lung squamous cell carcinoma dataset, pixel-level segmentation accuracy increases from 77.33% to 92.52% with lower prediction noise. Labeling time per slide drops from over 30 minutes to about 5 minutes using the semi-automated method.","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},368274,1790795890,{"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":52,"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},1099514068035,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nImproving lung cancer pathological hyperspectral diagnosis through cell-level annotation refinement  \nZhiliang Yan1, Haosong Huang1, Rongmei Geng3, Jingang Zhang1,2􀀍, Yu Chen3􀀍 & Yunfeng Nie4􀀍  \nLung cancer remains a major global health challenge, and accurate pathological examination is crucial for early detection. This study aims to enhance hyperspectral pathological image analysis by refining annotations at the cell level and creating a high-quality hyperspectral dataset of lung tumors. We address the challenge of coarse manual annotations in hyperspectral lung cancer datasets, which limit the effectiveness of deep learning models requiring precise labels for training. We propose a semiautomated annotation refinement method that leverages hyperspectral data to enhance pathological diagnosis. Specifically, we employ K-means unsupervised clustering combined with human-guided selection to refine coarse annotations into cell-level masks based on spectral features. Our method is validated using a hyperspectral lung squamous cell carcinoma dataset containing 65 image samples. Experimental results demonstrate that our approach improves pixel-level segmentation accuracy from 77.33% to 92.52% with a lower level of prediction noise. The time required to accurately label each pathological slide is significantly reduced. While pixel-level labeling methods for an entire slide can take over 30 mins, our semi-automated method requires only about 5 mins. To enhance visualization for pathologists, we apply a conservative post-processing strategy for instance segmentation. These results highlight the effectiveness of our method in addressing annotation challenges and improving the accuracy of hyperspectral pathological analysis.  \nLung cancer remains a leading global health challenge, with rising incidence and mortality rates. According to the International Agency for Research on Cancer (IARC), GLOBOCAN estimated 2.5 million new lung cancer cases (12.4% of all cancers) and 1.8 million deaths (18.7% of total cancer deaths) in 20221,2. As a result, lung cancer diagnosis and treatment have become critical public health priorities worldwide3. Currently, histopathology is the gold standard for diagnosing lung cancer4. Pathologists rely on morphological features observed through microscopes to classify cancer cells. However, this process is labor-intensive, time-consuming, costly, and prone to subjectivity, increasing the risk of misdiagnosis or missed diagnoses, especially when using conventional RGB imaging5. While whole slide images (WSI) have been widely used in tumor analysis, they are inherently limited by their reliance on spatial features such as cell size, texture, and color, which lack sufficient spectral information for capturing subtle pathological changes6.  \nHyperspectral Microscopic Imaging (HMI) presents a promising alternative by combining hyperspectral imaging (HSI) with microscopy7. Unlike traditional RGB imaging, which captures only three spectral bands visible to the human eye, HMI acquires spectral data across numerous narrow bands, providing richer biochemical and pathological information8,9. HMI can capture subtle spectral variations by analyzing the intensity at different spatial positions and wavelengths, providing significant advantages in identifying molecular and pathological changes in tissues10. This capability has enabled diverse medical applications9, including melanoma classification11, cervical cancer detection12, and diabetic complications research13. Machine learning (ML) techniques have been widely applied across various domains, including environmental studies, geosciences, and transportation analysis, demonstrating their effectiveness in predictive modeling14–16. For example, models have been developed to predict soil properties17 and analyze environmental changes18. Deep learning methods have achieved considerable success in lun","cbCaioypfullzvEP","https://ap.wps.com/l/cbCaioypfullzvEP","pdf",5028122,14,"English","# Introduction\n## Lung cancer and current histopathology workflow\n## Hyperspectral microscopic imaging (HMI)\n## ML and DL for hyperspectral segmentation\n## Annotation challenges and study motivation","[{\"question\":\"Why are accurate annotations critical for hyperspectral lung cancer diagnosis?\",\"answer\":\"Deep learning models for hyperspectral analysis require precise training labels. Coarse manual annotations can degrade model performance by limiting the quality of supervision.\"},{\"question\":\"What method does the study propose to refine coarse annotations?\",\"answer\":\"It proposes a semi-automated pipeline using K-means unsupervised clustering with human-guided selection, transforming coarse annotations into cell-level masks based on spectral features.\"},{\"question\":\"How much does the approach improve segmentation accuracy and labeling time?\",\"answer\":\"On a hyperspectral lung squamous cell carcinoma dataset, pixel-level segmentation accuracy increases from 77.33% to 92.52% with lower prediction noise. Labeling time per slide drops from over 30 minutes to about 5 minutes using the semi-automated method.\"}]","Improving lung cancer pathological hyperspectral diagnosis through cell-level annotation refinement | PDF",1790175981,35,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/348aaefc580c22a2ce47365826040102.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1b9badb6700be92defd32c93b471b459.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ccebd088a850dc20616b488eaeb575d0.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c059aa20534c816fb500b907e91fd174.webp",980,1287]