[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83539-en":3,"doc-seo-83539-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83539,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","CellPrior-Net: Prior-Guided Nuclei Detection and Classification for H&E Whole-Slide Images","Accurate nuclei detection and classification in hematoxylin and eosin (H&E) whole-slide images (WSIs) is fundamental to computational pathology, especially for quantitative tumor microenvironment analysis. The task is difficult because nuclei morphology, staining, scanners, organs, magnifications, and WSI artifacts vary widely. CellPrior-Net (CP-Net) introduces an efficient pipeline using a lightweight CNN and hematoxylin (H) channel priors to improve nuclei-aware feature learning. Benchmarks on 8 datasets (~10.4M nuclei) show comparable performance with faster inference. An end-to-end CellQuant-Net adds a quality assessment model to remove artifact regions before CP-Net detection and classification, enabling scalable downstream applications.","CellPrior-Net: Prior-Guided Nuclei Detection and Classification for H&E Whole-Slide Images  \nFalah Jabar1*, Pasquale Lombardi2, Aria Torkpour2, Masoud Tafavvoghi3, Per Niklas Benzler Waaler3, Sigve Andersen4, Erna-Elise Paulsen5, Mette Pøhl6, Lill-Tove Rasmussen Busund1, Tom Donnem4, Elin Richardsen1, David J. Pinato2, Mehrdad Rakaee7  \n1 Dep. of Clinical Pathology, University Hospital of North Norway, Tromsø, Norway  \n2 Dep. of Surgery and Cancer, Imperial College London, London, United Kingdom  \n3 Department of Medical Biology, UiT The Arctic University of Norway, Tromsø, Norway  \n4 Dep. of Clinical Medicine, UiT The Arctic University of Norway, Tromsø, Norway  \n5 Dep. of Pulmonology, University Hospital of North Norway, Tromsø, Norway  \n6 Dep. of Clinical Medicine, University of Copenhagen, Copenhagen  \n7 Dep. of Cancer Genetics, Oslo University Hospital, Oslo, Norway  \n*Corresponding author:  \nFalah Jabar, PhD  \nHansine Hansens veg 67, 9019 Tromsø, Norway  \nE-mail: [f.rahim@imperial.ac.uk](f.rahim@imperial.ac.uk)  \nAbstract—Accurate nuclei detection and classification in hematoxylin and eosin (H&E) whole-slide images (WSIs) is a key task in computational pathology, particularly for quantitative analysis of the tumor microenvironment. However, this task remains highly challenging due to variations in nuclei morphology, staining procedures, scanners, organs, magnifications, and WSI artifacts. In addition, many existing pipelines rely on computationally demanding architectures and post-processing procedures, making gigapixel WSI analysis time-consuming. In this work, CellPrior-Net (CP-Net) is proposed, an efficient nuclei detection and classification pipeline that utilizes a lightweight convolutional neural network architecture and hematoxylin (H) channel as prior information to enhance nuclei-aware feature learning. Extensive benchmarking was conducted against state-of-the-art pipelines on 8 public and private datasets (total:~ 10.4M nuclei) obtained from different organs, scanners, magnifications, and clinical centers. Experimental results demonstrate that CP-Net achieves comparable performance while significantly reducing inference time. Furthermore, CellQuant-Net was introduced–an end to end nuclei quantification pipeline–that integrates a quality assessment (QA) model to exclude regions with artifacts, followed by CP-Net cell detection and classification. The pipeline is publicly available on GitHub, and provides a potentially efficient and scalable framework for downstream computational pathology applications.  \nKeywords: Computational pathology, Computer vision, Digital pathology, Deep learning, Nuclei detection and classification, H&E Whole-slide images  \nI. Introduction  \nWhole-slide imaging enables the digitization of histopathology slides into gigapixel WSIs, providing detailed histological information. Since WSIs are extremely large and cannot be directly processed by deep learning (DL) models, they are divided into smaller image tiles (Fig. 1) . These tiles are subsequently used as input for various DL tasks, such as quantification, histological subtyping, genomic alterations, and treatment outcome prediction [1][2][3] .  \nSeveral pathology foundation models have been developed for computational pathology applications [4][5][6][7][8][9][10][11][12][13][14][15][16] . In particular, nuclei detection and classification have become a primary task, as they enable quantitative analysis of the tumor microenvironment and immune infiltration. Thus, several DL pipelines for nuclei detection and classification have been proposed [17][18][19][20][21][22][23][24][25] .  \nFig. 1. Examples showing the variability in nuclei appearance in H&E WSIs. Columns 1–5 present different tissue and nuclei patterns extracted from multiple WSIs. The first row shows the original H&E image tile, while the second and third rows show the separated hematoxylin (H) and eosin (E) .  \nHowever, up to date, accurate nuclei detection and classification","cbCaij4w7l3gzI2S","https://ap.wps.com/l/cbCaij4w7l3gzI2S","pdf",11021829,1,28,"English","en",105,"# Introduction\n## Challenges in nuclei detection and classification\n## Motivation for efficient prior-guided pipelines","[{\"question\":\"What makes nuclei detection and classification on H\\u0026E whole-slide images challenging?\",\"answer\":\"Variations in nuclei morphology, staining protocols, scanners, organs, magnifications, and WSI artifacts create strong domain shifts that can cause frequent model failures on unseen data.\"},{\"question\":\"How does CellPrior-Net (CP-Net) improve nuclei-aware feature learning?\",\"answer\":\"CP-Net uses a lightweight convolutional neural network and leverages the hematoxylin (H) channel as prior information to enhance learning while keeping inference efficient.\"},{\"question\":\"What is CellQuant-Net and how does it relate to CP-Net?\",\"answer\":\"CellQuant-Net is an end-to-end nuclei quantification pipeline that first applies a quality assessment model to exclude artifact regions, then runs CP-Net for nuclei detection and classification.\"}]",1784188700,71,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"cellprior-net-prior-guided-nuclei-detection-and-classification-for-he-whole-slide-images","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/cellprior-net-prior-guided-nuclei-detection-and-classification-for-he-whole-slide-images/83539/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What makes nuclei detection and classification on H&E whole-slide images challenging?","Question",{"text":75,"@type":76},"Variations in nuclei morphology, staining protocols, scanners, organs, magnifications, and WSI artifacts create strong domain shifts that can cause frequent model failures on unseen data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does CellPrior-Net (CP-Net) improve nuclei-aware feature learning?",{"text":80,"@type":76},"CP-Net uses a lightweight convolutional neural network and leverages the hematoxylin (H) channel as prior information to enhance learning while keeping inference efficient.",{"name":82,"@type":73,"acceptedAnswer":83},"What is CellQuant-Net and how does it relate to CP-Net?",{"text":84,"@type":76},"CellQuant-Net is an end-to-end nuclei quantification pipeline that first applies a quality assessment model to exclude artifact regions, then runs CP-Net for nuclei detection and classification.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]