[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-341591-105":59,"doc-detail-341591-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","a-lung-nodule-dataset-with-histopathology-based-cancer-type-annotation-publicly-accessible-data-and-tools","A Lung Nodule Dataset with Histopathology-based Cancer Type Annotation - Publicly Accessible Data and Tools","","The document introduces a lung Computed Tomography (CT) dataset designed to support medical diagnosis and more accurate cancer-type prediction in computer-aided diagnosis (CAD) workflows. It addresses the shortage of publicly available datasets with expert-level cancer type annotations. The dataset contains 330 nodules labeled as bounding boxes from 95 patients, and is benchmarked using classical classification and detection models to validate feasible auxiliary diagnostic applications.",{"@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":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/a-lung-nodule-dataset-with-histopathology-based-cancer-type-annotation-publicly-accessible-data-and-tools/341591/",{"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/a-lung-nodule-dataset-with-histopathology-based-cancer-type-annotation-publicly-accessible-data-and-tools/341591.png","ImageObject",300,407,{"name":92,"@type":93},"Ezra","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-09-22",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},"Why are CAD systems limited in predicting multiple cancer types for lung nodules?","Question",{"text":113,"@type":114},"They rely on publicly available datasets, and such datasets annotated with expert-level cancer type information are scarce, which reduces performance for multi-type prediction.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What does the proposed dataset contain?",{"text":118,"@type":114},"It includes 330 annotated lung nodules from 95 patients, where nodules are labeled as bounding boxes using lung CT images.",{"name":120,"@type":111,"acceptedAnswer":121},"How is the dataset evaluated in the document?",{"text":122,"@type":114},"The quality is assessed using classical classification and detection models, with results reported as promising for feasible auxiliary diagnosis.","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},341591,1790731178,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":34,"category_name":35,"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":52,"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},1099514068035,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \nopeN  \nDATA DeSCRipToR  \na Lung Nodule Dataset with Histopathology-based Cancer type annotation  \nMuwei Jian1,2 ✉, Hongyu Chen2,5, Zaiyong Zhang3,5, NanYang2,5, Haorang Zhang1, Lifu Ma4, Wenjing Xu2 & Huixiang Zhi2  \nRecently, Computer-Aided Diagnosis (CAD) systems have emerged as indispensable tools in clinical diagnostic workflows, significantly alleviating the burden on radiologists. Nevertheless, despite their integration into clinical settings, CAD systems encounter limitations. Specifically, while CAD systems can achieve high performance in the detection of lung nodules, they face challenges in accurately predicting multiple cancer types. This limitation can be attributed to the scarcity of publicly available datasets annotated with expert-level cancer type information. This research aims to bridge this gap by providing publicly accessible datasets and reliable tools for medical diagnosis, facilitating a finer categorization of different types of lung diseases so as to offer precise treatment recommendations. To achieve this objective, we curated a diverse dataset of lung Computed Tomography (CT) images, comprising 330 annotated nodules (nodules are labeled as bounding boxes) from 95 distinct patients. The quality of the dataset was evaluated using a variety of classical classification and detection models, and these promising results demonstrate that the dataset has a feasible application and further facilitate intelligent auxiliary diagnosis.  \nBackground & Summary  \nAt present, cancer stands as one of the most challenging diseases for medical professionals worldwide. According to the statistics of the International Agency for Research on Cancer (IARC) of the World Health Organization (WHO) in 20211, there were 2.21 million cases of lung cancer, accounting for 11% of all type cancers. Among them, 1.8 million people died of lung cancer bearing the proportion of 81% of the total number of lung cancer patients. It’s apparent that lung cancer has become the most prevalent and dangerous disease among various cancers.  \nNevertheless, ratifying to see that as technology evolves, the latest report of the American Cancer Society released in 2024, the mortality rate of lung cancer in the United States has dropped by 33%2. This is attributed to advancements in early lung cancer detection technology and corresponding treatment modalities. Currently, imaging scanning and pathological examination serve as two primary screening methods for lung cancer in differential diagnosis. The result of pathological examination is the gold standard for lung cancer diagnosis3. However, it is usually necessary to take biopsies by means of puncture or surgery, which is harmful to the human body and therefore unsuitable for routine examination. Both CT and chest X-ray photography are imaging inspection techniques based on radiology4,5, with the difference that X-ray is performed in anteroposterior or left-right overlapping views of the body, whereas CT is performed in cross-sectional views of the body. The National Lung Screening Trial (NLST) demonstrated that annual low-dose CT screening reduces lung cancer mortality in high-risk populations compared to annual chest X-ray screening6. This superiority can be attributed to CT’s capacity to visualize the three-dimensional structure of the lungs, thereby enabling more precise assessment of lesion location, size, and density. Consequently, CT screening significantly enhances the detection rate of lung cancer7,8. Nevertheless, it is still challenging to detect and identify benign and malignant pulmonary nodules based on CT. During a manual examination, an experienced physician should analyse a large number of CT images comprehensively, usually taking several minutes to thoroughly diagnose a patient, resulting in a  \n1School of computer Science and technology, Shandong University of finance and economics, Jinan, china. 2School of informati","cbCairfaCisBuQzg","https://ap.wps.com/l/cbCairfaCisBuQzg","pdf",1692861,"English","# Background & Summary\n## Motivation for CAD in lung cancer diagnosis\n## Dataset construction and annotation details\n## Dataset evaluation with classical models","[{\"question\":\"Why are CAD systems limited in predicting multiple cancer types for lung nodules?\",\"answer\":\"They rely on publicly available datasets, and such datasets annotated with expert-level cancer type information are scarce, which reduces performance for multi-type prediction.\"},{\"question\":\"What does the proposed dataset contain?\",\"answer\":\"It includes 330 annotated lung nodules from 95 patients, where nodules are labeled as bounding boxes using lung CT images.\"},{\"question\":\"How is the dataset evaluated in the document?\",\"answer\":\"The quality is assessed using classical classification and detection models, with results reported as promising for feasible auxiliary diagnosis.\"}]","A Lung Nodule Dataset with Histopathology-based Cancer Type Annotation - Publicly Accessible Data and Tools | PDF",1790042725,25]