COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images

By Linda Wang, Z. Q. Lin, Alexander Wong. 2020

2,747 citations recorded by the source corpus.

The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors’ knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors’ knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.

Subfields: Computer Vision and Pattern Recognition, Infectious Diseases, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Infectious Diseases

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Contrastive Learning of Medical Visual Representations from Paired Images and Text (2020, methodology): “…binary classiﬁcation of a chest image for ﬁve individual labels, i.e., atelectasis , cardiomegaly , consolidation , edema and pleural eﬀusion ; 3) COVIDx (Wang and Wong, 2020), which involves multi-class chest image classiﬁcation into three categories ( COVID19 , non-COVID pneumonia or normal );…”
Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images (2021, neutral): “Wang and Wong [16] used around 14k CXR images but reported an accuracy of 83.5% using a deep CNN, called COVID-Net.”
COVIDGR Dataset and COVID-SDNet Methodology for Predicting COVID-19 Based on Chest X-Ray Images (2020, methodology): “s. Examples of these repositories are: •RSNA Pneumonia CXR challenge dataset on Kaggle ([6]). •ChestX-ray8 dataset ([10]). •MIMIC-CXR dataset ([9]). •PadChest dataset ([7]). For instance, COVIDx 1.0 ([26]) was built by combining three public datasets: (i) COVID-19 Image Data Collection ([5]), (ii) F”
Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images (2020, methodology): “For example, a COVID-Net was proposed to detect COVID-19 cases from chest radiography images [16] .”
Automated detection of COVID-19 cases using deep neural networks with X-ray images (2020, methodology): “Few studies conducted prior to this study have used 25 and 50 images in each class [41, 42, 44, 45] .”
Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning Based Approach (2020, background): “Wang and Wong [18] designed a tailored deep learning-based framework, COVID-Net, developed for COVID-19 detection from chest X-ray images.”
CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection (2020, neutral): “The last step after the segmentation Wang and Wong [63] Deep Learning 92.30 Afshar, Heidarian, Naderkhani, Oikonomou, Plataniotis and Mohammadi [64] Capsule network 95.70 Chowdhury, Rahman, Khandakar, Mazhar, Kadir, Mahbub, Islam, Khan, Iqbal and Al-Emadi [30] Transfer Learning 97.94 Farooq and…”
Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets (2020, methodology): “Especially, Wang and Wong [6] proposed an open source deep convolutional neural network platform called COVID-”
Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, methodology): “For example, Wang et al. (2020a)† use a modified Inception neural network architecture (Szegedy et al., 2015) trained on regions of interest identified by radiologists to carry out binary classification between healthy patients and those infected with COVID-19.”
COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images (2020, positive): “The obtained COVIDx dataset [11] consists The main purpose of the selection of COVIDx dataset is that it is public available, so it is accessible for researchers and to be extensible.”
FLOP: Federated Learning on Medical Datasets using Partial Networks (2021, methodology): “COVIDx [29] is the open-access benchmark dataset with the largest number of COVID-19 positive patient cases, and is the combination of five publicly available COVID19 data repositories: (1) COVID-19 Image Data Collection [8], (2) COVID-19 Chest X-ray Dataset Initiative2, (3) Actualmed COVID19 Chest ”
COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images (2020, positive): “To conduct our experiments, we used the same dataset as Reference [9] .”
COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs (2020, methodology): “This works builds on the research presented in [7] , in hopes of building open source and open access techniques to help in the fight against the COVID-19 pandemic.”
Pneumonia Detection On Chest X-Ray Using Radiomic Features And Contrastive Learning (2021, background): “With the great success of deep learning in various fields, deep neural networks (DNNs) have proven to be powerful tools that can detect pneumonia to augment radiologists [3, 4, 5, 6].”
CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images (2020, methodology): “Wang and Wong [10] presented a residual deep architecture alled COVID-Net for detection of COVID-19 from chest X-ray imges.”
COVID-19 Image Data Collection: Prospective Predictions Are the Future (2020, methodology): “Results: When classifying between COVID/non-COVID most recent works using this dataset have taken other datasets and treated them as non-COVID-19 [Wang and Wong, 2020; Apostolopoulos and Mpesiana, 2020] while results with balanced datasets from Tartaglione et al. [2020] report much lower…”