COVIDGR Dataset and COVID-SDNet Methodology for Predicting COVID-19 Based on Chest X-Ray Images

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 COVID-19 triage systems and 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 article 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 Clínico 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 426 positive and 426 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 <inline-formula><tex-math notation="LaTeX">$\text{97.72}\% \pm \text{0.95}\%$</tex-math></inline-formula>, <inline-formula><tex-math notation="LaTeX">$\text{86.90}\% \pm \text{3.20}\%$</tex-math></inline-formula>, <inline-formula><tex-math notation="LaTeX">$\text{61.80}\% \pm \text{5.49}\%$</tex-math></inline-formula> in severe, moderate and mild COVID-19 severity levels. Our approach could help in the early detection of COVID-19. COVIDGR-1.0 along with the severity level labels are available to the scientific community through this link <uri>https://dasci.es/es/transferencia/open-data/covidgr/</uri>.

[1]  M. Lipsitch,et al.  Projecting the transmission dynamics of SARS-CoV-2 through the postpandemic period , 2020, Science.

[2]  Ioannis D. Apostolopoulos,et al.  Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks , 2020, Physical and Engineering Sciences in Medicine.

[4]  Charles E Kahn,et al.  How Might AI and Chest Imaging Help Unravel COVID-19’s Mysteries? , 2020, Radiology. Artificial intelligence.

[5]  Loris Nanni,et al.  A critic evaluation of methods for COVID-19 automatic detection from X-ray images , 2020, Information Fusion.

[6]  Antonio Pertusa,et al.  PadChest: A large chest x-ray image dataset with multi-label annotated reports , 2019, Medical Image Anal..

[7]  Yoshua Bengio,et al.  Predicting COVID-19 Pneumonia Severity on Chest X-ray With Deep Learning , 2020, Cureus.

[8]  Alexander Wong,et al.  COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images , 2020, Scientific reports.

[9]  A. Echenique,et al.  Chest X-Ray Findings in 636 Ambulatory Patients with COVID-19 Presenting to an Urgent Care Center: A Normal Chest X-Ray Is no Guarantee , 2020 .

[10]  Francisco Herrera,et al.  Big Data Preprocessing: Enabling Smart Data , 2020 .

[11]  U. Rajendra Acharya,et al.  Automated detection of COVID-19 cases using deep neural networks with X-ray images , 2020, Computers in Biology and Medicine.

[12]  M. Kuo,et al.  Frequency and Distribution of Chest Radiographic Findings in COVID-19 Positive Patients , 2019, Radiology.

[13]  Alexander Wong,et al.  COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest Radiography Images , 2020, ArXiv.

[14]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Till Döhmen,et al.  DeepCOVIDExplainer: Explainable COVID-19 Predictions Based on Chest X-ray Images , 2020, ArXiv.

[16]  Javier Ruiz Hidalgo,et al.  FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations , 2020, Inf. Fusion.

[17]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[18]  Siham Tabik,et al.  A snapshot of image pre-processing for convolutional neural networks: case study of MNIST , 2017, Int. J. Comput. Intell. Syst..

[19]  Farnoosh Naderkhani,et al.  COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images , 2020, Pattern Recognition Letters.

[20]  田中 利恵.  Radiological Society of North America : RSNA, 北米放射線学会 , 2010 .

[21]  Yiyan Song,et al.  Stability issues of RT‐PCR testing of SARS‐CoV‐2 for hospitalized patients clinically diagnosed with COVID‐19 , 2020, Journal of medical virology.

[22]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[23]  Joseph Paul Cohen,et al.  COVID-19 Image Data Collection , 2020, ArXiv.

[24]  Tatsuki Koyama,et al.  Severity scoring of lung oedema on the chest radiograph is associated with clinical outcomes in ARDS , 2018, Thorax.

[25]  Till Döhmen,et al.  DeepCOVIDExplainer: Explainable COVID-19 Diagnosis Based on Chest X-ray Images , 2020 .

[26]  Roger G. Mark,et al.  MIMIC-CXR: A large publicly available database of labeled chest radiographs , 2019, ArXiv.

[27]  Allan Tucker,et al.  Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection , 2020, ArXiv.

[28]  Yicheng Fang,et al.  Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR , 2020, Radiology.

[29]  Stefan Jaeger,et al.  Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. , 2014, Quantitative imaging in medicine and surgery.