BIMCV COVID-19: a large annotated dataset of RX and CT images from COVID-19 patients

Description

The BIMCV-COVID19+ dataset is a large dataset with chest X-ray CXR (CR, DX) and computed tomography (CT) images of COVID-19 patients along with their radiographic findings, pathologies, polymerase chain reaction (PCR), diagnostic immunoglobulin G (IgG) and immunoglobulin M (IgM) antibody tests and radiographic reports from the Medical Imaging Data Bank of the Valencian Community (BIMCV). The findings are mapped in standard terminology from the Unified Medical Language System (UMLS) and cover a broad spectrum of thoracic entities, in contrast to the much smaller number of entities noted in previous datasets. Images are stored in high resolution and entities are located with anatomical tags in a Medical Imaging Data Structure (MIDS) format. In addition, 23 images were annotated by a team of expert radiologists to include semantic segmentation of radiographic findings. In addition, extensive information is provided, such as the demographics of the patient, the type of projection and the acquisition parameters of the imaging study, among others. These database iterations include 7377 CR studies, 9463 DX and 6687 CT. This work is above all an open and free contribution of the authors of the working group with the support of the grant of the Ministry of Innovation, Universities, Science and Digital Society granted through decree 51/2020 by the Valencian Innovation Agency (Spain) and the Ministry of Health of the Valencian Community. This research is also supported by the UACOVID-19-18 project of the University of Alicante. Part of the infrastructure used has been co-financed by the European Union through the Operational Programme of the European Regional Development Fund (ERDF) of the Valencian Community 2014-2020. The Medical Imaging Bank of the Valencian Community has been partially funded by the Horizon 2020 Framework Programme of the European Union through grant agreement 688945 (Euro-BioImaging PrepPhase II).

Resources

Name Format Description Link
0 https://b2drop.bsc.es/index.php/s/BIMCV-COVID19-cIter_1_2-Negative
0 https://b2drop.bsc.es/index.php/s/BIMCV-COVID19-cIter_1_2

Tags

  • radiología
  • covid
  • imagen-médica
  • inteligencia-artificial

Topics

  • HEAL

Categories