This retrospective NIfTI image dataset consists of unenhanced chest CT images of CTs from 652 patients with COVID-19 infection from 652 patients in NIfTI file formatinfections. The images were retrospectively acquired at the point of care in an outbreak setting in China after from patients with Reverse Transcription Polymerase Chain Reaction (RT-PCR) confirmation for the presence of SARS-CoV-2.

Patients presented to a health care setting with a combination of symptoms, exposure to an infected patient, or travel history to an outbreak region. All patients had a positive RT-PCR for SARS-CoV-2 from a sample obtained within 1 day of the initial CT.  CT exams were performed with intravenous contrast and a soft tissue reconstruction algorithm.  The DICOM images were subsequently converted into NIfTI format. 

A multidisciplinary team trained several models using portions of this TCIA data set (, along with additional CTs and manually annotated images and other data &/or other CT’s)from other sources. A classification model derived in part from portions of this data (and also from other non-TCIA data) can be found this work is described at:  https://doi.org/10.1038/s41467-020-17971-2.  Models partly derived from portions of this data (and also from other data not shown here), may be found at:    The NVIDIA-related frameworks and models specific to this publication are available at no cost as part of the NVIDIA Clara Train SDK at https://ngc.nvidia.com/catalog/resourcescontainers/nvidia:clara:clara_ai_covid19_pipeline.A web-based research-only model (website ai-covid-19. This includes both inference-based pipelines for evaluation, as well as model weights for further training or fine tuning in outside institutions.  In addition, a web-based version of this model (for research use only) with drag-and-drop functionality for evaluating individual scans can be found at https://marketplace.arterys.com/model/nvidiacovidCT.  Upload of Uploading a CT yields a return email that contains results. This model is also partly derived from portions of this data (and also from other non-TCIA data) and is detailed at: https://doi.org/10.1038/s41467-020-17971-2.