{"url":"/dataset/u-10-united-10-covid19-ct-dataset","name":"U-10: United-10 COVID19 CT Dataset","full_name":"U-10: United-10 COVID19 CT Dataset","description_markdown":"This dataset supports the research detailed in the pre-print \"Virtual Imaging Trials Improved the Transparency and Reliability of AI Systems in COVID-19 Imaging.\" The study employs both clinical and simulated CT data to evaluate AI models for COVID-19 diagnosis. By leveraging the Virtual Imaging Trials (VIT) framework, the research addresses reproducibility and generalizability issues prevalent in medical imaging AI models.\r\n\r\nThe dataset includes:\r\n\r\nClinical CT Data: Drawn from 10 publicly available datasets, comprising over 12,000 volumes. These datasets span diverse populations, imaging protocols, and scanner configurations. Each of the 10 zip files contains pre-processed CT TFRecords (Train/Validation/Test)  used in the study. Detailed information about the data sources, pre-processing steps, and the inclusion and exclusion criteria can be found in the manuscript (https://arxiv.org/abs/2308.09730).\r\nSimulated CT Data: Generated using computational anatomical phantoms from the XCAT model and imaged with the DukeSim simulation framework. This synthetic dataset allows controlled experiments that isolate the effects of imaging physics and patient-specific factors. Can be available upon request through Center For virtual Imaging Trial Portal at https://cvit.duke.edu/\r\nThe accompanying study analyzes the performance of lightweight convolutional neural networks on both real and synthetic data, comparing results across multiple internal and external validation scenarios. Insights into factors such as infection severity, imaging dose, and modality type are explored.\r\n\r\nFor further details, visit our Project Page: https://fitushar.github.io/ReviCOVID.github.io/\r\nThe full source code is available on gitHub and GitLab\r\nGitHub: https://github.com/fitushar/CVIT_ReviCOVID19\r\nGitLab : https://gitlab.oit.duke.edu/cvit-public/cvit_revicovid19\r\n\r\nCitation:  When using this dataset, please cite the manuscript () and the original data-source.\r\nTushar et al., \"Virtual Imaging Trials Improved the Transparency and Reliability of AI Systems in COVID-19 Imaging\", arXiv:2308.09730.\r\n\r\nContact:  fakrulislam.tushar@duke.edu","description_withheld":null,"homepage":"https://zenodo.org/records/14064172","introduced_date":"2023-08-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/data-diversity-and-virtual-imaging-in-ai","title":"Virtual imaging trials improved the transparency and reliability of AI systems in COVID-19 imaging","first_author":"Fakrul Islam Tushar","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"3D Classification","url":"/task/3d-classification","datasets_with_task":"/datasets/task/3d-classification"}],"languages":[],"variants":["U-10: United-10 COVID19 CT Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-classification-on-u-10-united-10-covid19","task":"3D Classification","dataset_variant":"U-10: United-10 COVID19 CT Dataset","rows":2,"metrics":["AUC"],"first_row_in_archive_order":{"model":"U-10 Model","paper":"/paper/data-diversity-and-virtual-imaging-in-ai","metrics":{"AUC":"0.85"},"code_links":[{"title":"fitushar/CVIT_ReviCOVID19","url":"https://github.com/fitushar/CVIT_ReviCOVID19"},{"title":"cvit-public/cvit_revicovid19","url":"https://gitlab.oit.duke.edu/cvit-public/cvit_revicovid19"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/data-diversity-and-virtual-imaging-in-ai","title":"Virtual imaging trials improved the transparency and reliability of AI systems in COVID-19 imaging","date":"2023-08-17","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}