[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-352834-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-352834-en":130},{"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","petwb-rep-a-multi-cancer-whole-body-fdg-petct-dataset-with-corresponding-radiology-reports","PETWB-REP - a Multi-Cancer Whole-Body FDG PET/CT Dataset with Corresponding Radiology Reports","","Publicly available, large-scale medical imaging datasets are crucial for developing and validating AI models and enabling retrospective clinical research. PETWB-REP addresses the scarcity of multimodal resources by providing whole-body 18F-FDG PET/CT scans and corresponding fully de-identified radiology reports from 490 patients across diverse malignancies. The dataset is organized under the Brain Imaging Data Structure (BIDS) standard, offering raw data and processed derivatives with structured clinical metadata, supporting multi-center validation and downstream imaging, radiomics, and report generation research.",{"@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/petwb-rep-a-multi-cancer-whole-body-fdg-petct-dataset-with-corresponding-radiology-reports/352834/",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/petwb-rep-a-multi-cancer-whole-body-fdg-petct-dataset-with-corresponding-radiology-reports/352834.png","ImageObject",300,407,{"name":42,"@type":43},"Melati","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What does PETWB-REP include for each patient case?","Question",{"text":63,"@type":64},"PETWB-REP includes whole-body 18F-FDG PET/CT scans and fully de-identified radiology reports, along with structured clinical metadata.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How many patients and what cancer types are covered?",{"text":68,"@type":64},"The dataset includes 490 patients spanning multiple malignancies, including lung, liver, breast, prostate, and ovarian cancers, among others.",{"name":70,"@type":61,"acceptedAnswer":71},"What dataset organization and derived data formats are provided?",{"text":72,"@type":64},"PETWB-REP follows the Brain Imaging Data Structure (BIDS) standard and provides both raw data (with 3D defacing for privacy) and processed derivatives such as SUV-converted and registered outputs.","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},352834,1790469176,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":102,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},962085570644,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \noPEN  \nDATA DESCRIPToR  \nPEtWB-REP: a Multi-Cancer Whole-Body FDG PEt/Ct Dataset with Corresponding Radiology Reports  \nLe Xue1,2,7 ✉, Gang Feng3,4,7, Wenbo Zhang2,5, Yichi Zhang2,6, Lanlan Li5, Shuqi Wang5, Liling Peng4, Sisi Peng4 ✉ & XinGao4 ✉  \nPublicly available, large-scale medical imaging datasets are crucial for developing and validating artificial intelligence (AI) models and conducting retrospective clinical research. However, multimodal datasets that integrate functional and anatomical imaging with high-quality radiology reports across diverse malignancies remain scarce. Here, we present PETWB-REP, a curated dataset comprising whole-body 18F-Fluorodeoxyglucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT) scans and corresponding radiology reports from 490 patients. The cohort encompasses a broad spectrum of malignancies, including but not limited to lung, liver, breast, prostate, and ovarian cancers. Distinct from existing resources, PETWB-REP is organized following the Brain Imaging Data Structure (BIDS) standard, providing both raw data (with 3D de-facing for privacy) and processed derivatives (SUV-converted and registered). Each case includes bilingual (Chinese and English) de-identified textual reports and structured clinical metadata. This dataset is uniquely positioned to support multi-center validation and cross-disciplinary research in medical imaging, radiomics, automated report generation, and multimodal representation learning.  \nBackground & Summary  \n18F-FDG PET/CT remains a mainstay in cancer imaging for staging, monitoring, and treatment response evaluation1,2. The fusion of functional metabolic information from PET with detailed anatomical information from CT provides a comprehensive view of tumor burden and activity. While numerous studies have demonstrated the utility of PET/CT3–5, the public availability of large-scale, well-curated datasets remains limited. Existing resources often focus on a single cancer type, may lack corresponding clinical reports, or have limited sample sizes, which restricts the development of generalizable and robust computational models6–8.  \nThe rapid advancement of artificial intelligence (AI), particularly deep learning, has demonstrated the potential to transform the analysis of these complex medical images9–11. AI models are being developed to automate a range of tasks, from lesion detection and segmentation to the prediction of clinical outcomes12–16. However, the efficacy and generalizability of these models are fundamentally contingent upon the availability of large-scale, high-quality, and well-curated datasets.  \nTo address this gap, we constructed PETWB-REP, a dataset comprising 490 PET/CT studies from a single medical imaging center, encompassing a diverse cancer population. All cases include de-identified imaging data, fully anonymized radiology reports, and key clinical variables. This dataset enables a wide range of downstream research applications, including radiomic biomarker discovery, automated report generation, tumor segmentation, and multi-modal fusion learning.  \n1 Department of nuclear Medicine/Pet center, Huashan Hospital, fudan University, Shanghai, china. 2Shanghai Academy of Artificial Intelligence for Science, Shanghai, China. 3 Institute of Science and Technology for Braininspired intelligence, fudan University, Shanghai, china. 4Shanghai Universal Medical imaging Diagnostic center, Shanghai, china. 5Human Phenome institute, fudan University, Shanghai, china. 6Artificial Intelligence Innovation and incubation institute, fudan University, Shanghai, china. 7these authors contributed equally: Le Xue, Gang feng.  \n✉ e-mail: [lexue@fudan.edu.cn](lexue@fudan.edu.cn); [pengsisi@uvclinic.cn](pengsisi@uvclinic.cn); [gaoxin@uvclinic.cn](gaoxin@uvclinic.cn)  \n[www. nature.com/scientificdata/](www. nature.com/scientificdata/)  \nFig. 1 The distribution of cancer types in ","cbCaiurKrvf58raT","https://ap.wps.com/l/cbCaiurKrvf58raT","pdf",3929445,"English","# Background & Summary\n# Methods\n## Subject characteristics\n## Image acquisition protocol","[{\"question\":\"What does PETWB-REP include for each patient case?\",\"answer\":\"PETWB-REP includes whole-body 18F-FDG PET/CT scans and fully de-identified radiology reports, along with structured clinical metadata.\"},{\"question\":\"How many patients and what cancer types are covered?\",\"answer\":\"The dataset includes 490 patients spanning multiple malignancies, including lung, liver, breast, prostate, and ovarian cancers, among others.\"},{\"question\":\"What dataset organization and derived data formats are provided?\",\"answer\":\"PETWB-REP follows the Brain Imaging Data Structure (BIDS) standard and provides both raw data (with 3D defacing for privacy) and processed derivatives such as SUV-converted and registered outputs.\"}]","PETWB-REP - a Multi-Cancer Whole-Body FDG PET/CT Dataset with Corresponding Radiology Reports | PDF",1790101600,15,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3bcd065d26f2c30971037cb8eb57af33.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f2b47b7350678c3623f1675478d7a244.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3163d8a183adaff8903b1fa53ad6dbf2.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/90f7136feafcd6351d49646c02b020e5.webp",980,1287]