Imaging datasets
This section collects COVID-19 and pneumonia related chest x-ray datasets.
TorchXrayVision is a python library of chest X-ray datasets and models providing a standardized interface for some of the datasets listed below.
| Name | Publisher | Type | Images | Classes | Download links |
|---|---|---|---|---|---|
| COVID-19 image data collection | Joseph Paul Cohen | Chest x-ray / CT | 158 (updating) | COVID-19, SARS, Viral Pneumonia, etc. | http |
| NIH Clinical Center chest x-ray datasets | National Institutes of Health | Chest x-ray | 100,000+ | 14 categories including pneumonia | http; torrent: full, 224×224 |
| BIMCV-COVID19, BIMCV-PadChest | Medical Imaging Bank of the Valencia Region | Chest x-ray | 160,000+ | 174 labels (no COVID-19 yet) | http; torrent: full, 224×224 |
| RSNA Pneumonia Detection Challenge | Radiological Society of North America | chest x-ray | 26,684 | pneumonia object detection bboxes | kaggle (DICOM), torrent (jpeg) |
| CheXpert | Stanford Machine Learning Group | chest x-ray | 224,316 | 14 categories including pneumonia | http (registration needed) |
| MIMIC-CXR-JPG | Johnson et al. (2019) | chest x-ray | 300,000+ | 14 categories including pneumonia | http (credentialing needed) |
| Open-i | National Library of Medicine | chest x-ray | 7,470 | http: png, DICOM, labels | |
| COVID19 High quality images | theroyakash | Chest x-ray | 338 | COVID-19, Viral Pneumonia / Normal | kaggle |
| Chest X-Ray Images (Pneumonia) | Paul Mooney | Pediatric chest x-ray | 5,863 | Pneumonia / Normal | kaggle |
Case datasets
| Scope | Publisher | Granularity | Updated | Fields1 | Format | Dataset |
|---|---|---|---|---|---|---|
| International level | ||||||
| worldwide | Johns Hopkins CSSE | countries2 | daily | 1, 2, 3 | csv | link |
| worldwide | European Centre for Disease Prevention and Control | countries | daily | 1, 3 | xls | link |
| Country level | ||||||
| Canada | COVID-19 Canada Open Data Working Group | provinces | daily | 1, 2, 3, 7 | Google Sheets | link |
| Italy | Protezione Civile | national, regional, provinces | daily | n, r: 1, 2, 3, 4, 5, 6, 7; p: 1 | csv, json | link |
| United States | The COVID Tracking Project | states | daily | 1, 3, 7 | Google Sheets, csv, json, GraphQL | link |
[1] Fields explanation:
- Positive cases
- Recovered cases
- Deaths
- Hospitalized patients
- Patients in intensive care unit
- Cases in home confinement
- COVID-19 tests made
[2] provinces for China, US, Canada, Australia
Epidemic data and models
Collection of case datasets for analyzing the dynamics of the outbreak.
Case datasets
| Scope | Publisher | Granularity | Updated | Fields1 | Format | Dataset |
|---|---|---|---|---|---|---|
| International level | ||||||
| worldwide | Johns Hopkins CSSE | countries2 | daily | 1, 2, 3 | csv | link |
| worldwide | European Centre for Disease Prevention and Control | countries | daily | 1, 3 | xls | link |
| Country level | ||||||
| Canada | COVID-19 Canada Open Data Working Group | provinces | daily | 1, 2, 3, 7 | Google Sheets | link |
| Italy | Protezione Civile | national, regional, provinces | daily | n, r: 1, 2, 3, 4, 5, 6, 7; p: 1 | csv, json | link |
| United States | The COVID Tracking Project | states | daily | 1, 3, 7 | Google Sheets, csv, json, GraphQL | link |
[1] Fields explanation:
- Positive cases
- Recovered cases
- Deaths
- Hospitalized patients
- Patients in intensive care unit
- Cases in home confinement
- COVID-19 tests made
Government pages
Official pages for monitoring the national outbreaks with reported cases. English version is provided, if found.
Americas
Asia
Australia and Oceania
Europe
- Austria (in German)
- Belgium
- Denmark (in Danish)
- Estonia
- Finland
- France (in French)
- Germany (in German, see this page for situation reports in English)
- Hungary
- Ireland
- Italy (in Italian)
- Netherlands
- Norway
- Poland (in Polish)
- Portugal (in Portuguese)
- Spain (in Spanish)
- Sweden (in Swedish)
- Switzerland
- United Kingdom
Dashboards
Dashboards visualizing the dynamics of the outbreak in different geographic areas.
Worldwide
Country level
- Canada – Case level dashboard about the COVID-19 outbreak in Canada, curated by COVID-19 Canada Open Data Working Group
- Isreal – Government dashboard for monitoring the COVID-19 outbreak in Israel (in Hebrew)
- Italy – Official dashboard for monitoring the COVID-19 outbreak in Italy, provided by Civil Protection of Italy
- Portugal – Official dashboard for monitoring the COVID-19 outbreak in Portugal, provided by the Public Health Department of Portugal
- Singapore – Unoffical but extremly extensive dashboard for monitoring the COVID-19 outbreak in Singapore at case-level, provided by @zp_uca
- Spain – Official dashboard for monitoring the COVID-19 outbreak in Spain, provided by the Instituto de Salud Carlos III
Statistical models
- COVID-19 Dashboards – Extensive collection of dashboards, diagrams and other visualizations as well as statistical models of the COVID-19 outbreak.
- COVID-19 Health System Capacity – Open geospatial work to support healthcare systems’ capacity in the United States.
- Epidemic calculator – An interactive visual calculator demonstrating the relations between different epidemic variables.
- COVID-19 Scenarios – A planning tool for COVID-19 outbreaks in communities across the world.
Selected scientific articles
A collection of scientific papers related to COVID-19 relevant from the data science point of view.
- COVID-19 Open Research Dataset – A free resource of over 29,000 scholarly articles about COVID-19 and the coronavirus family of viruses
- Call to action of the US government on this dataset
- Kaggle challenge associated with the dataset
Medical imaging papers
Computer Tomography (CT) images
- Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT
- Lung Infection Quantification of COVID-19 in CT Images with Deep Learning
- Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for Automated Detection & Patient Monitoring using Deep Learning CT Image Analysis
- Deep Learning System to Screen Coronavirus Disease 2019 Pneumonia
- A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)
- Coronavirus Disease 2019 (COVID-19): A Perspective from China – A study discussing the use of different diagnosis tools (CT, x-ray) for early detection of COVID-19
Epidemic papers
- A Poisson Autoregressive Model to Understand COVID-19 Contagion Dynamics
- Relationship between the ABO Blood Group and the COVID-19 Susceptibility
Estimating the proportion of asymptomatic cases and transmissibility
- Substantial undocumented infection facilitates the rapid dissemination of novel coronavirus (SARS-CoV2)
- Estimating the asymptomatic proportion of coronavirus disease 2019 (COVID-19) cases on board the Diamond Princess cruise ship, Yokohama, Japan, 2020
- Evolving Epidemiology and Impact of Non-pharmaceutical Interventions on the Outbreak of Coronavirus Disease 2019 in Wuhan, China
- Estimation of the asymptomatic ratio of novel coronavirus infections (COVID-19)
- Clinical presentation and virological assessment of hospitalized cases of coronavirus disease 2019 in a travel-associated transmission cluster
- SARS-CoV-2 Viral Load in Upper Respiratory Specimens of Infected Patients
Clinical record analysis
- Prediction of criticality in patients with severe Covid-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan
- Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner
Computational drug research
- Repurposing Therapeutics for COVID-19: Supercomputer-Based Docking to the SARS-CoV-2 Viral Spike Protein and Viral Spike Protein-Human ACE2 Interface