{"id":46039,"date":"2023-11-20T05:48:56","date_gmt":"2023-11-20T11:48:56","guid":{"rendered":"https:\/\/stage.cancerimagingarchive.net\/analysis-result\/plethora\/"},"modified":"2025-03-20T13:44:32","modified_gmt":"2025-03-20T18:44:32","slug":"plethora","status":"publish","type":"tcia_analysis_result","link":"https:\/\/stage.cancerimagingarchive.net\/analysis-result\/plethora\/","title":{"rendered":"PLETHORA"},"featured_media":8967,"template":"","class_list":["post-46039","tcia_analysis_result","type-tcia_analysis_result","status-publish","has-post-thumbnail"],"cancer_types":["Lung"],"citations":[45967,45969,45971,45973,45975,45977,45979,45981,45983,45985,45987,45989,45991,45993,45995,9225],"result_doi":"10.7937\/tcia.2020.6c7y-gq39","result_download_info":"","result_downloads":[45999,46001,46003,46005,46007,46009],"version_change_log_archived":"Version 3 (Current): Updated 2020\/07\/28\r\n   Data TypeDownload all or Query\/FilterCorresponding Original CT Images (DICOM) from NSCLC-Radiomics (24 GB)Thoracic Segmentations (NIfTI, 26.9 MB)Pleural Effusion Segmentations (NIfTI, 1.7 MB)\u00a0Segmentation Features and Image Metadata\u00a0(CSV)Baseline UNet 2D Summary (PDF)Baseline UNet 3D Summary (PDF)Data Dictionary (DOCX)\r\nVersion 3 changes:\r\n2D U-Net\r\nIncorrectly reported the 2D U-Net achieved segmentations with\u00a0Dice similarity coefficients of 0.90 and 0.94 for left and right lungs.The performances should be 0.94 and 0.94.\u00a0\r\n3D U-Net\r\nIncorrectly reported the 3D U-Net achieved segmentations with\u00a0Dice similarity coefficients of 0.82 and 0.94 for left and right lungs.The performances should be 0.95 and 0.96.\r\nData Dictionary\u00a0\r\nAdded Auto-MS Thorax DSC\u00a0description.Version 2: 2020\/06\/26\r\n   Data TypeDownload all or Query\/FilterCorresponding Original CT Images (DICOM) from NSCLC-Radiomics (24 GB)Thoracic Segmentations (NIfTI, 26.9 MB)Pleural Effusion Segmentations (NIfTI, 1.7 MB)\u00a0Segmentation Features and Image Metadata\u00a0(CSV)Baseline UNet 2D Summary (PDF)Baseline UNet 3D Summary (PDF)Data Dictionary (DOCX)\r\nVersion 2 changes:\r\nThe dataset is now named \u201cPleThora\u201d for \u201cPleural effusion and thoracic cavity segmentations in diseased lungs.\u201dAll NIfTI files have been compressed for convenience (.nii \u00e0 .nii.gz)All thoracic cavity primary reviewer segmentations have been renamed from \u201clungMask_edit.nii\u201d to \u201c[CaseID]_thor_cav_primary_reviewer.nii.gz\u201d to more specifically identify each file\u2019s contents and avoid confusion.Eighty-six thoracic cavity secondary reviewer segmentations have been added. These are named \u201c[CaseID]_thor_cav_secondary_reviewer.nii.gz.\u201dInterobserver variability analysis between primary and secondary reviewer thoracic cavity segmentations revealed four cases in which interobserver agreement was anomalously lower than all other cases. These cases were manually re-reviewed by another physician. In three cases (LUNG1-026, LUNG1-157, and LUNG1-354) it was deemed that the secondary reviewer\u2019s segmentation excluded structures that should have been included. These were corrected. In one case (LUNG-088) it was determined that the primary reviewer segmentation included a large (400 cm3) nodal conglomerate. Our original thoracic cavity segmentation definition did not intend to include nodal conglomerates, so for consistency\u2019s sake we corrected the primary reviewer segmentation accordingly. However, the segmentation with the nodal conglomerate is still valuable, so we provide it as well and name it \u201cLUNG1-088_thor_cav_primary_reviewer_with_nodal_conglomerate.nii\u201dWe manually reviewed the pleural effusion segmentations of the primary physician reviewer and determined that in many cases the reviewer had not been sufficiently careful. Therefore, all 78 primary reviewer segmentations were re-reviewed by another physician and corrected as necessary. They are now re-submitted as \u201c[CaseID]_effusion_first_reviewer.nii.gz\u201dSeventy-eight pleural effusion secondary reviewer segmentations have been added. These are named \u201c[CaseID]_effusion_second_reviewer.nii.gz.\u201dFifteen pleural effusion tertiary reviewer segmentations have been added. These are named \u201c[CaseID]_effusion_third_reviewer.nii.gz.\u201dWe add two documents that describe baseline performances for 2D and 3D U-Net segmentation algorithms and define a reproducible train\/test split.Data Dictionary: we provide a data dictionary to describe the meanings of column names in the \u201cThorax and Pleural Effusion Segmentation Metadata\u201d spreadsheet.Version 1: 2020\/04\/03\r\n   Data TypeDownload all or Query\/FilterThoracic Segmentations (NIfTI, 54.7 MB zipped, 23.6 GB uncompressed)Pleural Effusion Segmentations (NIfTI, 5.3 MB zipped, 4.9 GB uncompressed)\u00a0Segmentation Features and Image Metadata\u00a0(CSV)Corresponding Original CT Images (DICOM) from NSCLC-Radiomics (24 GB)","versions":[46035,46037],"additional_resources":"","cancer_locations":["Lung"],"publications_related":"","result_page_accessibility":"Public","detailed_description":"All NIfTI files have been compressed for convenience (.nii.gz)\r\n\r\n<u><strong>Note<\/strong><\/u>: These segmentations use the RPI orientation, but the original DICOM files are oriented using the RAI convention.\u00a0 As a result, some tools such as ITK-SNAP will not render the segmentations in the correct orientation when visualized.\u00a0 The authors of these data suggest using software like <a href=\"https:\/\/mangoviewer.com\/\">Mango (http:\/\/ric.uthscsa.edu\/mango\/)<\/a> or to convert to DICOM files to NIfTI with software like dcm2niix (<a href=\"https:\/\/github.com\/rordenlab\/dcm2niix\">https:\/\/github.com\/rordenlab\/dcm2niix<\/a>) to address this issue.","publications_using":"","result_title":"Thoracic Volume and Pleural Effusion Segmentations in Diseased Lungs for Benchmarking Chest CT Processing Pipelines","species":["Human"],"version_number":"3","date_updated":"2020-07-28","related_collections":[43005],"result_short_title":"PleThora","subjects":"402","related_analysis_results":false,"result_browse_title":"Thoracic Volume and Pleural Effusion Segmentations in Diseased Lungs for Benchmarking Chest CT Processing Pipelines (PleThora)","supporting_data":false,"version_change_log":"<strong>Version 3 changes:<\/strong>\r\n\r\n<u>2D U-Net<\/u>\r\n<ul>\r\n \t<li><span style=\"color: #212121;\">Incorrectly reported the 2D U-Net achieved segmentations with\u00a0Dice similarity coefficients of 0.90 and 0.94 for left and right lungs.<\/span><\/li>\r\n \t<li><span style=\"color: #212121;\">The performances should be 0.94 and 0.94.\u00a0<\/span><\/li>\r\n<\/ul>\r\n<u><span style=\"color: #212121;\">3D U-Net<\/span><\/u>\r\n<ul>\r\n \t<li><span style=\"color: #212121;\">Incorrectly reported the 3D U-Net achieved segmentations with\u00a0Dice similarity coefficients of 0.82 and 0.94 for left and right lungs.<\/span><\/li>\r\n \t<li>The performances should be 0.95 and 0.96.<\/li>\r\n<\/ul>\r\n<u><span style=\"color: #003366;\">Data Dictionary\u00a0<\/span><\/u>\r\n<ul>\r\n \t<li>Added <em>Auto-MS Thorax DSC<\/em>\u00a0description.<\/li>\r\n<\/ul>","collections":"Below is a list of the Collections used in these analyses:\r\n<table><colgroup> <col \/> <col \/> <col \/><\/colgroup>\r\n<tbody>\r\n<tr>\r\n<th>Source Data Type<\/th>\r\n<th>Download<\/th>\r\n<th>License<\/th>\r\n<\/tr>\r\n<tr>\r\n<td>Corresponding Original CT Images from <a href=\"https:\/\/cancerimagingarchive.net\/collection\/nsclc-radiomics\/\" target=\"_blank\" rel=\"noopener\">NSCLC-Radiomics<\/a> (DICOM, 402 subjects, 24 GB)<\/td>\r\n<td>\r\n<div>\r\n\r\n<a href=\"\/wp-content\/uploads\/NSCLC-Radiomics-OriginalCTs.tcia\" download=\"NSCLC-Radiomics-OriginalCTs.tcia\"><button><i><\/i> Download<\/button><\/a>\r\n\r\n(Download requires\u00a0<a href=\"https:\/\/wiki.cancerimagingarchive.net\/display\/NBIA\/Downloading+TCIA+Images\">NBIA Data Retriever<\/a>)\r\n\r\n<\/div><\/td>\r\n<td>\r\n<div>\r\n\r\n<a href=\"https:\/\/creativecommons.org\/licenses\/by\/3.0\/\">CC BY 3.0<\/a>\r\n\r\n<\/div><\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n&nbsp;","result_summary":"Automated or semi-automated algorithms intended for chest CT analyses typically require the creation of a 3D map of the thoracic volume as their initial step. Identifying this anatomic region precedes fundamental tasks such as lung structure segmentation, lesion detection, and radiomics feature extraction in analysis pipelines. However, automatic approaches to segment the thoracic volume maps struggle to perform consistently in subjects with diseased lungs \u2013 yet this is exactly the circumstance for which pipeline analyses would be most useful.\r\n\r\nTo address this need, we have created PleThora, a dataset of <strong>ple<\/strong>ural effusion and <strong>thora<\/strong>cic cavity segmentations in subjects with diseased lungs. PleThora consists of left and right thoracic cavity segmentations delineated on 402 CT scans from The Cancer Imaging Archive\u00a0<a href=\"\/collection\/nsclc-radiomics\/\">NSCLC-Radiomics<\/a>\u00a0collection as well as separate segmentations labeling pleural effusions alone. Thoracic cavity segmentations include lung parenchyma, tumor, atelectasis, adhesions, and effusion. PleThora is a tool for medical image preprocessing and segmentation researchers to build and compare approaches for region-of-interest identification and analysis.\r\n\r\nThe thoracic cavity segmentations were generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student, and revised by a radiation oncologist or a radiologist.\u00a0 Pleural effusion segmentations were manually delineated by a medical student and revised by a radiologist. Expert GTV segmentations already provided by the\u00a0<a href=\"\/collection\/nsclc-radiomics\/\" target=\"_blank\" rel=\"noopener\">NSCLC-Radiomics<\/a> collection helped inform our segmentations, and areas of the effusion that overlap with GTVs are not included. Researchers interested in discriminating between GTV and effusion using imaging biomarker inputs may find our pleural effusion segmentations useful, especially when paired with the GTV segmentations provided in the\u00a0<a href=\"\/collection\/nsclc-radiomics\/\" target=\"_blank\" rel=\"noopener\">NSCLC-Radiomics<\/a> collection.\r\n\r\nTabular data are also provided, including GTV, thorax, and effusion volumes (in cm3), tumor location, and image metadata. Additionally, we standardized a train\/test split for training deep learning algorithms with the thoracic cavity segmentations.\r\n\r\n<u><strong>Note<\/strong><\/u>: These segmentations use the RPI orientation, but the original DICOM files are oriented using the RAI convention.\u00a0 As a result, some tools such as ITK-SNAP will not render the segmentations in the correct orientation when visualized.\u00a0 The authors of these data suggest using software like <a href=\"https:\/\/mangoviewer.com\/\">Mango (http:\/\/ric.uthscsa.edu\/mango\/)<\/a> or to convert to DICOM files to NIfTI with software like dcm2niix (<a href=\"https:\/\/github.com\/rordenlab\/dcm2niix\">https:\/\/github.com\/rordenlab\/dcm2niix<\/a>) to address this issue.","collection_downloads":[46011],"result_featured_image":{"ID":"8967","post_author":"29","post_date":"2023-09-14 01:02:58","post_date_gmt":"2023-09-14 06:02:58","post_content":"","post_title":"Screen-Shot-2020-03-31-at-4.00.06-PM","post_excerpt":"","post_status":"inherit","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"screen-shot-2020-03-31-at-4-00-06-pm","to_ping":"","pinged":"","post_modified":"2023-11-20 05:48:57","post_modified_gmt":"2023-11-20 11:48:57","post_content_filtered":"","post_parent":"46039","guid":"https:\/\/stage.cancerimagingarchive.net\/wp-content\/uploads\/Screen-Shot-2020-03-31-at-4.00.06-PM.png","menu_order":"0","post_type":"attachment","post_mime_type":"image\/png","comment_count":"0","pod_item_id":"8967"},"result_acknowledgements":"We would like to acknowledge the individuals and institutions that have provided data for this collection:\r\n<ul>\r\n \t<li>University of Texas M.D. Anderson Cancer Center,\u00a0 Houston, TX,\u00a0 USA\u00a0- Special thanks to Kendall Kiser, MS Biomedical Informatics, from the Department of Radiation Oncology.<\/li>\r\n \t<li>The University of Texas Health Science Center School of Biomedical Informatics,\u00a0 Houston, TX,\u00a0 USA<\/li>\r\n \t<li>John P. and Kathrine G. McGovern Medical School, Houston, TX. Department of Diagnostic and Interventional Imaging.<\/li>\r\n<\/ul>","hide_from_browse_table":"0","program":["Community"],"_links":{"self":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results\/46039","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\/46039\/revisions"}],"predecessor-version":[{"id":47439,"href":"https:\/\/stage.cancerimagingarchive.net\/api\/v1\/analysis-results\/46039\/revisions\/47439"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/stage.cancerimagingarchive.net\/api\/wp\/v2\/media\/8967"}],"wp:attachment":[{"href":"https:\/\/stage.cancerimagingarchive.net\/api\/wp\/v2\/media?parent=46039"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}