Long COVID Iowa-UNICAMP

Diedre S Carmo; Alejandro A Pezzulo; Raul A Villacreses; McKenna L Eisenbeisz; Rachel L Anderson; Sarah E Van Dorin; Leticia Rittner; Roberto A Lotufo; Sarah E Gerard; Joseph M Reinhardt; Alejandro P Comellas

doi:10.25820/data.007301

Back

Dataset

Open access

Long COVID Iowa-UNICAMP

Diedre S Carmo, Alejandro A Pezzulo, Raul A Villacreses, McKenna L Eisenbeisz, Rachel L Anderson, Sarah E Van Dorin, Leticia Rittner, Roberto A Lotufo, Sarah E Gerard, Joseph M Reinhardt, …

University of Iowa

06/17/2024

DOI: 10.25820/data.007301

Files and links (9)

txt

README8.02 kBDownload View

READMEData creators, funding, abstract, file information, and methods.Open Data Commons Attribution (ODC-By) V1.0, Open Access

longciu_1_tgt.nii179.76 kBDownload View

Open Data Commons Attribution (ODC-By) V1.0, Open Access

longciu_2_tgt.nii140.84 kBDownload View

Open Data Commons Attribution (ODC-By) V1.0, Open Access

longciu_3_tgt.nii162.34 kBDownload View

Open Data Commons Attribution (ODC-By) V1.0, Open Access

longciu_img.nii27.44 MBDownload View

Open Data Commons Attribution (ODC-By) V1.0, Open Access

Abstract

The field of supervised automated medical imaging segmentation suffers from the lack of annotated groundtruth data. This problem is even more noticeable when dealing with the segmentation of multiple types of lung findings in computed tomography with uncertain borders, such as opacities and parenchymal consolidation resulting from pneumonia. In this work, we make available the first public dataset of ground glass opacity and consolidation in the lung of Long COVID patients. The Long COVID Iowa-UNICAMP dataset (LongCIU) was built by three independent expert annotators, blindly segmenting the same 90 selected axial slices manually, without using any automated initialization. We make available not only the final consensus segmentation, but also the individual segmentation from each annotator totaling 360 slices. This dataset can be used to train and validate new automated segmentation methods and to study interrater uncertainty in lung opacities' segmentation on computed tomography. For further detail please see written file (README)

Computed Tomography

Pulmonary Diseases

Post COVID-19

COVID-19

Segmentation

Details

Title: Subtitle: Long COVID Iowa-UNICAMP
Creators: Diedre S Carmo (Author) - Universidade Estadual de Campinas (UNICAMP)
Alejandro A Pezzulo (Author) - University of Iowa, Pulmonary, Critical Care, and Occupational Medicine
Raul A Villacreses (Author) - University of Iowa, Pulmonary, Critical Care, and Occupational Medicine
McKenna L Eisenbeisz (Author)
Rachel L Anderson (Author) - University of Iowa
Sarah E Van Dorin (Author)
Leticia Rittner (Author) - Universidade Estadual de Campinas (UNICAMP)
Roberto A Lotufo (Author) - Universidade Estadual de Campinas (UNICAMP)
Sarah E Gerard (Author) - University of Iowa, Roy J. Carver Department of Biomedical Engineering
Joseph M Reinhardt (Author) - University of Iowa, Roy J. Carver Department of Biomedical Engineering
Alejandro P Comellas (Author) - University of Iowa, Pulmonary, Critical Care, and Occupational Medicine
Resource Type: Dataset
DOI: 10.25820/data.007301
Publisher: University of Iowa
Grants: Automated longitudinal segmentation of lung and COVID-19 findings exploring self-supervised learning and polymorphic training, 2022/02344-8, Fundação de Amparo à Pesquisa do Estado de São Paulo (Brazil, São Paulo) - FAPESP
Language: English
Date collected: 06/26/2020–06/26/2020
Date published: 06/17/2024
Academic Unit: Pulmonary, Critical Care, and Occupational Medicine; Health Management and Policy; ICTS; Iowa Neuroscience Institute; Internal Medicine
Record Identifier: 9984632558202771

Metrics

96 File views/ downloads

392 Record Views

Long COVID Iowa-UNICAMP

Files and links (9)

Related content

Abstract

Details

Metrics