[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-330288-105":59,"doc-detail-330288-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","diagset-a-dataset-for-prostate-cancer-histopathological-image-classification","DiagSet - a dataset for prostate cancer histopathological image classification","","Introduces DiagSet, a histopathological dataset for prostate cancer detection, comprising over 2.6 million tissue patches from 430 fully annotated whole-slide imaging (WSI) scans, plus 4675 scans with binary diagnoses and 46 scans independently labeled by histopathologists. Proposes a machine-learning framework for cancerous tissue localization and scan-level diagnosis using uncertainty-aware abstention. An ensemble of deep neural networks at multiple scales reaches 94.6% patch-level accuracy and yields scan-level agreement comparable to nine human experts.",{"@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":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/diagset-a-dataset-for-prostate-cancer-histopathological-image-classification/330288/",{"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/diagset-a-dataset-for-prostate-cancer-histopathological-image-classification/330288.png","ImageObject",300,407,{"name":92,"@type":93},"Finn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-12","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is DiagSet in this paper?","Question",{"text":113,"@type":114},"DiagSet is a histopathological dataset containing annotated prostate tissue regions from WSI scans, including patch-level annotations and scan-level binary diagnoses.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method handle uncertain cases?",{"text":118,"@type":114},"The framework uses thresholding to abstain from decisions when cases are uncertain.",{"name":120,"@type":111,"acceptedAnswer":121},"What performance and validation results are reported?",{"text":122,"@type":114},"The ensemble achieves 94.6% accuracy at the patch level and shows high scan-level statistical agreement with nine human histopathologists, with results largely within the doctors’ correlation range.","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},330288,1790363027,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"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":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDiagSet: a dataset for prostate cancer histopathological image classification  \nMichał Koziarski1,2,3*, Bogusław Cyganek1,2, Przemysław Niedziela2, Bogusław Olborski1, Zbigniew Antosz1, Marcin Żydak1, Bogdan Kwolek1,2, Paweł Wąsowicz1, Andrzej Bukała2, Jakub Swadźba1,4 & Piotr Sitkowski1  \nCancer diseases constitute one of the most significant societal challenges. In this paper, we introduce a novel histopathological dataset for prostate cancer detection. The proposed dataset, consisting of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnoses, and 46 scans with diagnoses independently provided by a group of histopathologistscan be found at [https://github.com/michalkoziarski/DiagSet](https://github.com/michalkoziarski/DiagSet. Furthermore)[. Furthermore](https://github.com/michalkoziarski/DiagSet. Furthermore), we propose a machine learning framework for detection of cancerous tissue regions and prediction of scan-level diagnosis, utilizing thresholding to abstain from the decision in uncertain cases. The proposed approach, composed of ensembles of deep neural networks operating on the histopathological scans at different scales, achieves 94.6% accuracy in patch-level recognition and is compared in a scan-level diagnosis with 9 human histopathologists showing high statistical agreement.  \nIn highly developed countries, prostate cancer is the second most common cause of death in men after lung cancer. Prostate cancer is one of the most common malignant neoplasms in men. Treatment method choice depends mainly on the clinical stage and malignancy determined by a specialist histopathologist according to the Gleason scale1–3 and the ISUP classification 2014 by the ISUP grade group4. However, the number of professional doctors is limited and continues to decline compared to social needs. A way out of this situation is using modern technologies based on deep learning and the necessary repositories of labeled data to train them.  \nIn this paper, we present and share a new set of histopathological data, called DiagSet, containing the annotated regions of prostate tissues in the whole slide imaging (WSI) scans characterized by different Gleason degrees. We also present the structure and the results of the operation of the individual deep convolutional neural networks (CNNs) and vision transformers (ViTs) as well as an ensemble of the deep convolutional neural networks appropriately trained for the classification of histopathological images of the prostate WSI. First, AlexNet5, VGG16, VGG196, ResNet507, Inception V38, and ViT-B/329 networks were trained and their performance analysed. Second, these convolutional networks were used again, but this time cooperating in an ensemble, wherein each classifier was trained with images of a different magnification factor, after which the individual probabilities returned by each network were combined to produce the final result. Then few rules have been developed and used to produce the binary diagnosis. The best binary classification ratio obtained with the ensemble architecture is 94.58%. An experiment was then conducted in which nine volunteer professional histopathology doctors participated, making individual diagnoses on a set of forty-six anonymous WSI scans. Then the correlations oftheir responses were computed, as well as correlations oftheir responses with respect to the machine given diagnosis by the proposed method. The conducted statistical analysis showed that, except for one WSI scan, the examination correlation of the machine response is within the correlation range obtained between the participating doctors.  \nRegarding the literature and recent works, the classification of histopathological scans can be realized by various types of CNN5,6,8, 10, 11, recurrent neural networks (RNN), as well as autoencoders (AE)7, generative adversarial netwo","cbCaiea2HV090iXB","https://ap.wps.com/l/cbCaiea2HV090iXB","pdf",1636241,14,"English","# DiagSet Dataset Overview\n## Dataset Composition and Annotation\n## Machine Learning Framework and Uncertainty Handling\n## Deep Ensemble Models and Network Architectures\n## Scan-Level Diagnosis and Human Agreement\n## Background: Gleason Scale and Related Work","[{\"question\":\"What is DiagSet in this paper?\",\"answer\":\"DiagSet is a histopathological dataset containing annotated prostate tissue regions from WSI scans, including patch-level annotations and scan-level binary diagnoses.\"},{\"question\":\"How does the proposed method handle uncertain cases?\",\"answer\":\"The framework uses thresholding to abstain from decisions when cases are uncertain.\"},{\"question\":\"What performance and validation results are reported?\",\"answer\":\"The ensemble achieves 94.6% accuracy at the patch level and shows high scan-level statistical agreement with nine human histopathologists, with results largely within the doctors’ correlation range.\"}]","DiagSet - a dataset for prostate cancer histopathological image classification | PDF",1789988011,35]