{
  "id": "2006.01409",
  "version": "v1",
  "published": "2020-06-02T06:18:34.000Z",
  "updated": "2020-06-02T06:18:34.000Z",
  "title": "COVIDGR dataset and COVID-SDNet methodology for predicting COVID-19 based on Chest X-Ray images",
  "authors": [
    "S. Tabik",
    "A. Gómez-Ríos",
    "J. L. Martín-Rodríguez",
    "I. Sevillano-García",
    "M. Rey-Area",
    "D. Charte",
    "E. Guirado",
    "J. L. Suárez",
    "J. Luengo",
    "M. A. Valero-González",
    "P. García-Villanova",
    "E. Olmedo-Sánchez",
    "F. Herrera"
  ],
  "categories": [
    "eess.IV",
    "cs.CV"
  ],
  "abstract": "Currently, Coronavirus disease (COVID-19), one of the most infectious diseases in the 21st century, is diagnosed using RT-PCR testing, CT scans and/or Chest X-Ray (CXR) images. CT (Computed Tomography) scanners and RT-PCR testing are not available in most medical centers and hence in many cases CXR images become the most time/cost effective tool for assisting clinicians in making decisions. Deep learning neural networks have a great potential for building triage systems for detecting COVID-19 patients, especially patients with low severity. Unfortunately, current databases do not allow building such systems as they are highly heterogeneous and biased towards severe cases. This paper is three-fold: (i) we demystify the high sensitivities achieved by most recent COVID-19 classification models, (ii) under a close collaboration with Hospital Universitario Cl\\'inico San Cecilio, Granada, Spain, we built COVIDGR-1.0, a homogeneous and balanced database that includes all levels of severity, from Normal with positive RT-PCR, Mild, Moderate to Severe. COVIDGR-1.0 contains 377 positive and 377 negative PA (PosteroAnterior) CXR views and (iii) we propose COVID Smart Data based Network (COVID-SDNet) methodology for improving the generalization capacity of COVID-classification models. Our approach reaches good and stable results with an accuracy of $97.37\\% \\pm 1.86 \\%$, $88.14\\% \\pm 2.02\\%$, $66.5\\% \\pm 8.04\\%$ in severe, moderate and mild COVID severity levels. Our approach could help in the early detection of COVID-19. COVIDGR-1.0 dataset will be made available after the review process.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-02T06:18:34.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "chest x-ray images",
      "covid-sdnet methodology",
      "covidgr dataset",
      "hospital universitario clinico san cecilio",
      "mild covid severity levels"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}