[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369130-105":59,"doc-detail-369130-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","deep-learning-enabled-scoring-of-pancreatic-neuroendocrine-tumors-based-on-cancer-infiltration-patterns","Deep Learning Enabled Scoring of Pancreatic Neuroendocrine Tumors Based on Cancer Infiltration Patterns","","Pancreatic neuroendocrine tumors (PanNETs) are heterogeneous neoplasms whose histomorphologic subtypes correlate with distinct prognoses. Beyond WHO grading, a recent PanNET categorization approach scores infiltration patterns at the tumor–non-neoplastic parenchyma interface (tumor-NNP interface), but human assessment creates intra- and inter-observer variability. This study proposes a deep learning computational pipeline that automatically categorizes PanNETs using entity-graphs over cells and a graph neural network (GNN) that integrates pathology domain knowledge. Tested on 105 HE-stained whole slide images, the domain-knowledge-integrated method achieves a 76.70% test F1-score.",{"@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/deep-learning-enabled-scoring-of-pancreatic-neuroendocrine-tumors-based-on-cancer-infiltration-patterns/369130/",{"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/deep-learning-enabled-scoring-of-pancreatic-neuroendocrine-tumors-based-on-cancer-infiltration-patterns/369130.png","ImageObject",300,407,{"name":92,"@type":93},"Lucas Martin","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What new parameter is used for PanNET categorization in the study?","Question",{"text":112,"@type":113},"The study focuses on scoring infiltration patterns at the tumor–non-neoplastic parenchyma (tumor-NNP) interface for PanNET categorization.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why is automated scoring needed for PanNETs?",{"text":117,"@type":113},"Existing categorizations can require human judgment, which leads to intra- and inter-observer variability, motivating automated systems using quantitative metrics.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the proposed method perform the automated categorization?",{"text":121,"@type":113},"It constructs entity-graphs on cells and trains a graph neural network (GNN) on these graphs, integrating pathology domain knowledge into the GNN construction and training.","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},369130,1790804508,{"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":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},8796095360427,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Endocrine Pathology (2025) 36:2  \n[https://doi.org/10.1007/s12022-025-09846-3](https://doi.org/10.1007/s12022-025-09846-3)  \nDeep Learning Enabled Scoring of Pancreatic Neuroendocrine Tumors Based on Cancer Infiltration Patterns  \nSoner Koc1,2 · Ozgur Can Eren3,4 · Rohat Esmer6 · Fatma Ulkem Kasapoglu1,2 · Burcu Saka3,4 · Orhun Cig Taskin3,4 · Pelin Bagci5 · Nazmi Volkan Adsay3,4,6 · Cigdem Gunduz‑Demir1,2,6  \nAccepted: 10 January 2025 / Published online: 23 January 2025 © The Author(s) 2025  \nAbstract  \nPancreatic neuroendocrine tumors (PanNETs) are a heterogeneous group of neoplasms that include tumors with different histomorphologic characteristics that can be correlated to sub-categories with different prognoses. In addition to the WHO grading scheme based on tumor proliferative activity, a new parameter based on the scoring of infiltration patterns at the interface of tumor and non-neoplastic parenchyma (tumor-NNP interface) has recently been proposed for PanNET categorization. Despite the known correlations, these categorizations can still be problematic due to the need for human judgment, which may involve intra-and inter-observer variability. Although there is a great need for automated systems working on quantitative metrics to reduce observer variability, there are no such systems for PanNET categorization. Addressing this gap, this study presents a computational pipeline that uses deep learning models to automatically categorize PanNETs for the first time. This pipeline proposes to quantitatively characterize PanNETs by constructing entity-graphs on the cells, and to learn the PanNET categorization using a graph neural network (GNN) trained on these graphs. Different than the previous studies, the proposed model integrates pathology domain knowledge into the GNN construction and training for the purpose of a deeper utilization of the tumor microenvironment and its architectural changes for PanNET categorization. We tested our model on 105 HE stained whole slide images of PanNET tissues. The experiments revealed that this domain knowledge integrated pipeline led to a 76.70% test set F1-score, resulting in significant improvements over its counterparts.  \nKeywords Pancreatic neuroendocrine tumors · Infiltration patterns · Graph neural networks · Deep learning · Artificial intelligence  \nSoner Koc and Ozgur Can Eren contributed equally to this article and share first authorship.  \n* Nazmi Volkan Adsay [vadsay@ku.edu.tr](vadsay@ku.edu.tr)  \n* Cigdem Gunduz-Demir[cgunduz@ku.edu.tr](cgunduz@ku.edu.tr)  \n1 Department of Computer Engineering, Koc University, Istanbul, Turkey  \n2 KUIS AI Center, Koc University, Istanbul, Turkey  \n3 Department of Pathology, Koc University School of Medicine, Istanbul, Turkey  \n4 Koc University Research Center for Translational Medicine, Istanbul, Turkey  \n5 Department of Pathology, Marmara University Pendik Research and Training Hospital, Istanbul, Turkey  \n6 Koc University School of Medicine, Istanbul, Turkey  \nIntroduction  \nPancreatic neuroendocrine tumors (PanNET) are the second most common malignant neoplasms of the pancreas, and their incidence is on the rise. Compared to the more common adenocarcinomas of this organ, which are highly aggressive malignancies (currently the third leading cause of cancer-related deaths in the US [1]), PanNETs have a significantly better clinical outcome. However, their accurate management has been very problematic due to the highly variable behavior of the cases, with some patients cured with resection while others with similar disease succumb in a few years.  \nCurrently, PanNETs without distant metastasis are treated with watchful waiting if \u003C 2 cm, and pancreatectomy if >2 cm as the standard treatment suggested by guidelines [2] . However, many patients on watchful waiting progress, and which ones will do so is a major concern. Similarly,  \npredicting the behavior after resection, and determining which patients are more prone to progression and metastas","cbCaiothf4Uf4GDD","https://ap.wps.com/l/cbCaiothf4Uf4GDD","pdf",1908564,"English","# Abstract\n## Introduction","[{\"question\":\"What new parameter is used for PanNET categorization in the study?\",\"answer\":\"The study focuses on scoring infiltration patterns at the tumor–non-neoplastic parenchyma (tumor-NNP) interface for PanNET categorization.\"},{\"question\":\"Why is automated scoring needed for PanNETs?\",\"answer\":\"Existing categorizations can require human judgment, which leads to intra- and inter-observer variability, motivating automated systems using quantitative metrics.\"},{\"question\":\"How does the proposed method perform the automated categorization?\",\"answer\":\"It constructs entity-graphs on cells and trains a graph neural network (GNN) on these graphs, integrating pathology domain knowledge into the GNN construction and training.\"}]","Deep Learning Enabled Scoring of Pancreatic Neuroendocrine Tumors Based on Cancer Infiltration Patterns | PDF",1790180891,25,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a664c5ce22e571085f6ebf1d65b7a561.webp",983,1305,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ca6355124de2b36c041d9d5b86d951c5.webp",982,1304,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3ed8332c0bb7e8cf0dc9b627d850e1b0.webp",981,1303,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/578047d0ba0062ce7c0d5b85fff27525.webp",980,1301]