[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-352568-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-352568-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","a-high-magnifications-histopathology-image-dataset-for-oral-squamous-cell-carcinoma-diagnosis-and-prognosis","A High Magnifications Histopathology Image Dataset for Oral Squamous Cell Carcinoma Diagnosis and Prognosis","","A high-resolution histopathology image dataset, Multi-OSCC, is introduced to address limitations of existing oral squamous cell carcinoma resources, which often include small cohorts and focus on either diagnosis or prognosis alone. Multi-OSCC contains 1,325 OSCC patients represented by six images per patient across ×200, ×400, and ×1000, covering core and edge tumor regions, and provides rich annotations for recurrence prediction and multiple diagnostic tasks. The dataset is evaluated using visual encoders, multi-image fusion, stain normalization, and multi-task learning, and is publicly released for future 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/a-high-magnifications-histopathology-image-dataset-for-oral-squamous-cell-carcinoma-diagnosis-and-prognosis/352568/",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/a-high-magnifications-histopathology-image-dataset-for-oral-squamous-cell-carcinoma-diagnosis-and-prognosis/352568.png","ImageObject",300,407,{"name":42,"@type":43},"Margaret","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-23","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",13,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What does the Multi-OSCC dataset provide?","Question",{"text":63,"@type":64},"It provides 1,325 OSCC patients with six high-resolution histopathology images per patient and annotations covering both diagnostic and prognostic clinical tasks.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which magnifications and tumor regions are included?",{"text":68,"@type":64},"Images are captured at ×200, ×400, and ×1000, with two images per magnification covering both core and edge tumor regions.",{"name":70,"@type":61,"acceptedAnswer":71},"What clinical tasks are annotated in Multi-OSCC?",{"text":72,"@type":64},"The dataset includes six tasks: recurrence prediction (REC), lymph node metastasis (LNM), tumor differentiation (TD), tumor invasion (TI), cancer embolus (CE), and perineural invasion (PI).","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},352568,1790511181,{"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},137451207643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \nOPEN  \nDATA DESCRIPTOR  \nA High Magnifications Histopathology Image Dataset for OralSquamous Cell Carcinoma Diagnosis and Prognosis  \nJinquan Guan1,5, Junhong Guo2,5, Qi Chen3, JianChen1, Yongkang Cai2, Yilin He2, Zhiquan Huang2, Yan Wang2 ✉ &Yutong Xie4 ✉  \nOral Squamous Cell Carcinoma (OSCC) is a prevalent and aggressive malignancy where deep learningbased computer-aided diagnosis and prognosis can enhance clinical assessments. However, existing publicly available OSCC datasets often suffer from limited patient cohorts and a restricted focus on either diagnostic or prognostic tasks, limiting the development of comprehensive and generalizable models. To bridge this gap, we introduce Multi-OSCC, a new histopathology image dataset comprising 1,325 OSCC patients, integrating both diagnostic and prognostic information to expand existing public resources. Each patient is represented by six high resolution histopathology images captured at ×200,×400, and ×1000—two per magnification—covering both the core and edge tumor regions. The MultiOSCC dataset is richly annotated for six critical clinical tasks: recurrence prediction (REC), lymph node metastasis (LNM), tumor differentiation (TD), tumor invasion (TI), cancer embolus (CE), and perineural invasion (PI). We systematically evaluate the impact of different visual encoders, multi-image fusion techniques, stain normalization, and multi-task learning frameworks to benchmark this dataset. To accelerate future research, we publicly release the Multi-OSCC dataset at: [https://github.com/](https://github.com/)[ ](https://github.com/)guanjinquan/OSCC-PathologyImageDataset.  \nBackground & Summary  \nOral squamous cell carcinoma (OSCC) is one of the most common malignant tumors ofthe head and neck, with over 380,000 new cases and approximately 180,000 deaths reported globally in 20221. It primarily affects the mucosal surfaces ofthe oral cavity and is strongly associated with risk factors such as tobacco use, alcohol consumption, and HPV infection. Early detection and accurate staging are critical, as OSCC can invade surrounding tissues and metastasize to regional lymph nodes, significantly worsening prognosis2. Histopathological examination of biopsy specimens remains the gold standard for diagnosis and staging, involving tissue processing, staining, and microscopic analysis by pathologists. This process enables clinicians to assess tumor differentiation, invasion depth, lymph node involvement, and other key prognostic indicators3. Despite advancementsin imaging and molecular diagnostics, histopathology continues to play a central role in treatment planning and predicting patient outcomes.  \nIn recent years, AI has shown promise in automating pathology image analysis, enhancing diagnostic speed, accuracy, and consistency4,5. Crucially, growing evidence suggests that the micro-morphological phenotype of the primary tumor encodes latent information reflecting the tumor’s aggressive biological behavior and interaction with the systemic environment. Krogue et al. (2023) demonstrated that machine-learned histological features derived solely from primary colorectal tumor slides could independently predict lymph node metastasis and stratify patient survival risk, validating the capability of local morphological patterns to forecast systemic outcomes6. In the context of OSCC, Vollmer et al. (2024) used a random survival forest on clinical, genomic, and  \n1School of Software Engineering, South China University of Technology, Guangzhou, China. 2 Department of Oral and Maxillofacial Surgery, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China .  \n3School of computer Science, University of Adelaide, Adelaide, Australia. 4 Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE. 5These authors contributed equally: Jinquan Guan, Junhong Guo. ✉e-mail:  \n[wangy573@mail.sysu.edu.cn](wangy573@mail.sysu.edu.c","cbCaifD2IbKR12zH","https://ap.wps.com/l/cbCaifD2IbKR12zH","pdf",5287482,14,"English","# Background & Summary\n## Dataset Overview\n## Task Definitions and Annotations\n## Benchmarking and Evaluation\n## Public Release","[{\"question\":\"What does the Multi-OSCC dataset provide?\",\"answer\":\"It provides 1,325 OSCC patients with six high-resolution histopathology images per patient and annotations covering both diagnostic and prognostic clinical tasks.\"},{\"question\":\"Which magnifications and tumor regions are included?\",\"answer\":\"Images are captured at ×200, ×400, and ×1000, with two images per magnification covering both core and edge tumor regions.\"},{\"question\":\"What clinical tasks are annotated in Multi-OSCC?\",\"answer\":\"The dataset includes six tasks: recurrence prediction (REC), lymph node metastasis (LNM), tumor differentiation (TD), tumor invasion (TI), cancer embolus (CE), and perineural invasion (PI).\"}]","A High Magnifications Histopathology Image Dataset for Oral Squamous Cell Carcinoma Diagnosis and Prognosis | PDF",1790100274,35,[148,152,156,160],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0fb6247775a8f40b44e63f033b641c7c.webp",983,1291,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/eae76432cae46bd1a1cbef5132caf008.webp",982,1290,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a6d654b4c3247094a634eadcfee3f1f7.webp",981,1289,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/49081369e9b3dbb26005578f1af146ca.webp",980,1287]