[Paper Review] COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images

Ezz El‐Din Hemdan, Marwa A. Shouman+1 more|arXiv (Cornell University)|Mar 24, 2020

COVID-19 diagnosis using AIMedicine41 references972 citations

TL;DR

Introduces COVIDX-Net, a framework of seven deep CNN architectures to classify COVID-19 from chest X-ray images using a small dataset; reports competitive f1-scores for normal and COVID-19 classes.

ABSTRACT

Background and Purpose: Coronaviruses (CoV) are perilous viruses that may cause Severe Acute Respiratory Syndrome (SARS-CoV), Middle East Respiratory Syndrome (MERS-CoV). The novel 2019 Coronavirus disease (COVID-19) was discovered as a novel disease pneumonia in the city of Wuhan, China at the end of 2019. Now, it becomes a Coronavirus outbreak around the world, the number of infected people and deaths are increasing rapidly every day according to the updated reports of the World Health Organization (WHO). Therefore, the aim of this article is to introduce a new deep learning framework; namely COVIDX-Net to assist radiologists to automatically diagnose COVID-19 in X-ray images. Materials and Methods: Due to the lack of public COVID-19 datasets, the study is validated on 50 Chest X-ray images with 25 confirmed positive COVID-19 cases. The COVIDX-Net includes seven different architectures of deep convolutional neural network models, such as modified Visual Geometry Group Network (VGG19) and the second version of Google MobileNet. Each deep neural network model is able to analyze the normalized intensities of the X-ray image to classify the patient status either negative or positive COVID-19 case. Results: Experiments and evaluation of the COVIDX-Net have been successfully done based on 80-20% of X-ray images for the model training and testing phases, respectively. The VGG19 and Dense Convolutional Network (DenseNet) models showed a good and similar performance of automated COVID-19 classification with f1-scores of 0.89 and 0.91 for normal and COVID-19, respectively. Conclusions: This study demonstrated the useful application of deep learning models to classify COVID-19 in X-ray images based on the proposed COVIDX-Net framework. Clinical studies are the next milestone of this research work.

Motivation & Objective

• Motivate automated COVID-19 diagnosis from chest X-ray images to assist radiologists.
• Propose a framework (COVIDX-Net) using multiple deep CNN architectures to classify COVID-19 status from X-ray images.
• Evaluate performance on a small, early public dataset and demonstrate feasibility of deep learning in this context.

Proposed method

• Explore seven CNN architectures, including modified VGG19 and MobileNet v2, as classifiers within COVIDX-Net.
• Use normalized image intensities as input features for classification.
• Train on 80% of the data and test on 20% to assess COVID-19 detection performance.
• Provide a framework that outputs negative vs. positive COVID-19 status for a given X-ray image.

Experimental results

Research questions

• RQ1 Can a framework of multiple CNN architectures effectively classify COVID-19 from chest X-ray images despite limited data?
• RQ2 Which architectures within COVIDX-Net yield the best balance of sensitivity and specificity for COVID-19 detection?
• RQ3 How does COVIDX-Net performance compare between normal and COVID-19 classes on the available dataset?

Key findings

• On the available dataset, VGG19 and DenseNet variants achieved similar automated COVID-19 classification performance.
• Reported f1-scores: 0.89 for the normal class and 0.91 for the COVID-19 class.
• The study demonstrates the usefulness of deep learning models to classify COVID-19 in X-ray images within the proposed framework.