{"id":45965,"date":"2023-11-20T05:45:29","date_gmt":"2023-11-20T11:45:29","guid":{"rendered":"https:\/\/stage.cancerimagingarchive.net\/analysis-result\/pan-cancer-nuclei-seg\/"},"modified":"2024-12-06T13:31:32","modified_gmt":"2024-12-06T19:31:32","slug":"pan-cancer-nuclei-seg","status":"publish","type":"tcia_analysis_result","link":"https:\/\/stage.cancerimagingarchive.net\/analysis-result\/pan-cancer-nuclei-seg\/","title":{"rendered":"PAN-CANCER-NUCLEI-SEG"},"featured_media":8941,"template":"","class_list":["post-45965","tcia_analysis_result","type-tcia_analysis_result","status-publish","has-post-thumbnail"],"cancer_types":["Bladder Urothelial Carcinoma","Breast Invasive Carcinoma","Cervical Squamous Cell Carcinoma","Endocervical Adenocarcinoma","Glioblastoma Multiforme","Lung Adenocarcinoma","Lung Squamous Cell Carcinoma","Pancreatic adenocarcinoma","Prostate Adenocarcinoma","Skin Cutaneous Melanoma","Uterine Corpus Endometrial Carcinoma","Colon adenocarcinoma","Rectal Adenocarcinoma","Stomach Adenocarcinoma","Uveal Melanoma"],"citations":[45949,45951,9225],"result_doi":"10.7937\/TCIA.2019.4A4DKP9U","result_download_info":"","result_downloads":[45953,45955,45957,45959,45961,45963],"version_change_log_archived":"Version 1 (Current): 2020\/02\/08\r\n   Data TypeDownload all or Query\/FilterTissue Slide Images (SVS, 1,200 GB)  List of histopathology slides (TXT,  348.5 KB )WSI quality control results (TXT, 151.4 KB)Segmentation region checking results (TXT, 169.4 KB)","versions":false,"additional_resources":"Additional information about\r\n<ul>\r\n \t<li>Additional visual segmentation data can be found on <a href=\"https:\/\/pathdb.cancerimagingarchive.net\/\">PathDB<\/a><\/li>\r\n \t<li>Manual nucleus segmentation data of 1,365 patches: These 1,365 patches are randomly extracted from all 14 cancer types mentioned above. This data contains original H&amp;E stained histopathology image patches, and instance-level segmentation masks. the process is in the\u00a0<a href=\"\/wp-content\/uploads\/Read-Me.docx\" download=\"Read-Me.docx\" data-linked-resource-container-id=\"64685083\" data-linked-resource-container-version=\"24\" data-linked-resource-content-type=\"application\/vnd.openxmlformats-officedocument.wordprocessingml.document\" data-linked-resource-default-alias=\"Read Me.docx\" data-linked-resource-id=\"96337976\" data-linked-resource-type=\"attachment\" data-linked-resource-version=\"1\" data-nice-type=\"Word Document\">readme.docx<\/a> file and<\/li>\r\n \t<li>a crosswalk between patch filenames and TCGA case identifiers are within\u00a0<a href=\"\/wp-content\/uploads\/Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" download=\"Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" data-linked-resource-container-id=\"64685083\" data-linked-resource-container-version=\"24\" data-linked-resource-content-type=\"text\/plain\" data-linked-resource-default-alias=\"Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" data-linked-resource-id=\"140313374\" data-linked-resource-type=\"attachment\" data-linked-resource-version=\"1\" data-nice-type=\"Text File\">Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt<\/a> file.<\/li>\r\n<\/ul>","cancer_locations":["Bladder","Brain","Breast","Colon","Eye","Lung","Pancreas","Prostate","Rectum","Stomach","Uterus","Endometrium"],"publications_related":"<span style=\"color: #ffffff;\">.<\/span>","result_page_accessibility":"Public","detailed_description":"Additional visual segmentation data can be found on <a href=\"https:\/\/pathdb.cancerimagingarchive.net\/\">PathDB<\/a>\r\n\r\n<strong>Manual nucleus segmentation data of 1,365 patches<\/strong>\r\n\r\nThese 1,365 patches are randomly extracted from all 14 cancer types mentioned above. This data contains original H&amp;E stained histopathology image patches, and instance-level segmentation masks. Additional information about the process is in the <a href=\"\/wp-content\/uploads\/Read-Me.docx\" download=\"Read-Me.docx\" data-linked-resource-container-id=\"64685083\" data-linked-resource-container-version=\"24\" data-linked-resource-content-type=\"application\/vnd.openxmlformats-officedocument.wordprocessingml.document\" data-linked-resource-default-alias=\"Read Me.docx\" data-linked-resource-id=\"96337976\" data-linked-resource-type=\"attachment\" data-linked-resource-version=\"1\" data-nice-type=\"Word Document\">readme.docx<\/a> file and a crosswalk between patch filenames and TCGA case identifiers are within <a href=\"\/wp-content\/uploads\/Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" download=\"Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" data-linked-resource-container-id=\"64685083\" data-linked-resource-container-version=\"24\" data-linked-resource-content-type=\"text\/plain\" data-linked-resource-default-alias=\"Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt\" data-linked-resource-id=\"140313374\" data-linked-resource-type=\"attachment\" data-linked-resource-version=\"1\" data-nice-type=\"Text File\">Pan-Cancer-Nuclei-Seg_1365patches_to_TCGA-ID_readme.txt<\/a> file.","publications_using":"TCIA maintains <a href=\"https:\/\/www.cancerimagingarchive.net\/publications\/\"> a list of publications<\/a> that leverage TCIA data. If you have a manuscript you'd like to add please <a href=\"http:\/\/www.cancerimagingarchive.net\/support\/\">contact the TCIA Helpdesk<\/a>.","result_title":"Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images","species":false,"version_number":"1","date_updated":"2020-02-08","related_collections":[43811,44347,44097,43835,44257,43903,43753,44187,44377,44129,44211],"result_short_title":"Pan-Cancer-Nuclei-Seg","subjects":"5204","related_analysis_results":false,"result_browse_title":"Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images (Pan-Cancer-Nuclei-Seg)","supporting_data":["Nuclei segmentations"],"version_change_log":"","collections":"Below is a list of the Collections used in these analyses:\r\n<ul>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.8LNG8XDR\">TCGA-BLCA<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.AB2NAZRP\">TCGA-BRCA<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.SQ4M8YP4\">TCGA-CESC<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.HJJHBOXZ\">TCGA-COAD<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.RNYFUYE9\">TCGA-GBM<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.JGNIHEP5\">TCGA-LUAD<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.TYGKKFMQ\">TCGA-LUSC<\/a>,<\/li>\r\n \t<li>TCGA-PAAD,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.YXOGLM4Y\">TCGA-PRAD<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.F7PPNPNU\">TCGA-READ<\/a>,<\/li>\r\n \t<li>TCGA-SKCM,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.GDHL9KIM\">TCGA-STAD<\/a>,<\/li>\r\n \t<li><a href=\"https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.GKJ0ZWAC\">TCGA-UCEC<\/a>,<\/li>\r\n \t<li>TCGA-UVM<\/li>\r\n<\/ul>","result_summary":"Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology. Existing state-of-the-art approaches demand extensive amounts of supervised training data from pathologists and may still perform poorly in images from unseen tissue types. We propose an unsupervised approach for histopathology image segmentation that synthesizes heterogeneous sets of training image patches, of every tissue type. Although our synthetic\u00a0patches are not always of high quality, we harness the motley crew of generated samples through a generally applicable importance sampling method.\r\n\r\nThis proposed approach,\u00a0for the first time, re-weighs the training loss over synthetic data so that the ideal (unbiased) generalization loss over\u00a0the true data distribution is minimized. This enables us\u00a0to use a random polygon generator to synthesize approximate cellular structures (i.e., nuclear masks) for which no real examples are given in many tissue types, and hence,\u00a0GAN-based methods are not suited. In addition, we propose a hybrid synthesis pipeline that utilizes textures in real histopathology patches and GAN models, to tackle heterogeneity in tissue textures.\u00a0 Compared with existing state-of-the-art supervised models, our approach generalizes significantly better on cancer types without training data. Even\u00a0in cancer types with training data, our approach achieves the same performance without supervision cost.\r\n\r\nIn this dataset we release code and nucleus segmentations in whole slide tissue images with quality control results for Whole Slide Images (WSI) in The Cancer Genome Atlas (TCGA) repository from 5,204 subjects (6,142 slide images).\u00a0 Within this total, there are two subsets of data: (1) automatic nucleus segmentation data of 5,060 whole slide tissue images of 10 cancer types, with quality control results, and (2) manual nucleus segmentation data of 1,356 image patches from the same 10 cancer types plus additional 4 cancer types.\r\n<h4>5,060 Whole Slide Images (WSIs) are from the following 10 cancer types:<\/h4>\r\n<strong> BLCA <\/strong> Bladder urothelial carcinoma\r\n<strong> BRCA <\/strong> Breast invasive carcinoma\r\n<strong> CESC <\/strong> Cervical squamous cell carcinoma and endocervical adenocarcinoma\r\n<strong> GBM <\/strong> Glioblastoma Multiforme\r\n<strong> LUAD <\/strong> Lung adenocarcinoma\r\n<strong> LUSC <\/strong> Lung squamous cell carcinoma\r\n<strong> PAAD <\/strong> Pancreatic adenocarcinoma\r\n<strong> PRAD <\/strong> Prostate adenocarcinoma\r\n<strong> SKCM <\/strong> Skin Cutaneous Melanoma\r\n<strong> UCEC <\/strong> Uterine Corpus Endometrial Carcinoma\r\n\r\nNote that you can also download segmentation data of following 4 cancer types, although they are not officially verified.\r\n\r\n<strong>COAD<\/strong> Colon adenocarcinoma\r\n<strong>READ<\/strong> Rectal adenocarcinoma\r\n<strong>STAD<\/strong> Stomach adenocarcinoma\r\n<strong>UVM<\/strong> Uveal Melanoma","collection_downloads":false,"result_featured_image":{"ID":"8941","post_author":"29","post_date":"2023-09-14 01:02:16","post_date_gmt":"2023-09-14 06:02:16","post_content":"","post_title":"image002","post_excerpt":"","post_status":"inherit","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"image002","to_ping":"","pinged":"","post_modified":"2023-11-20 05:45:31","post_modified_gmt":"2023-11-20 11:45:31","post_content_filtered":"","post_parent":"45965","guid":"https:\/\/stage.cancerimagingarchive.net\/wp-content\/uploads\/image002.png","menu_order":"0","post_type":"attachment","post_mime_type":"image\/png","comment_count":"0","pod_item_id":"8941"},"result_acknowledgements":"","hide_from_browse_table":"0","program":["Community"],"_links":{"self":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results\/45965","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results"}],"about":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/wp\/v2\/types\/tcia_analysis_result"}],"version-history":[{"count":1,"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results\/45965\/revisions"}],"predecessor-version":[{"id":47489,"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results\/45965\/revisions\/47489"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/stage.cancerimagingarchive.net\/api\/wp\/v2\/media\/8941"}],"wp:attachment":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/wp\/v2\/media?parent=45965"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}