Classification of COVID-19 Infection in Posteroanterior Chest X-rays

Classification of COVID-19 Infection in Posteroanterior Chest X-rays With Common Deep Learning Architectures

The objective of this study is to assess three configurations of two convolutional deep neural network architectures for the classification of COVID-19 PCX images.

Study Overview

• Status: Completed
• Conditions: COVID-19
• Intervention / Treatment: Device: CovX

Detailed Description

The December 2019 outbreak of COVID-19 has now evolved into a public health emergency of global concern. Given the rapid spread of infection, the rapid depletion of hospital resources due to high influxes of patients, and the current absence of specific therapeutic drugs and vaccines for treatment of COVID-19 infection, it is essential to detect onset of the disease at its early stages. Radiological examinations, the most common of which are posteroanterior chest X-ray (PCX) images, play an important role in the diagnosis of COVID-19. The objective of this study is to assess three configurations of two convolutional deep neural network architectures for the classification of COVID-19 PCX images. The primary experimental dataset consisted of 115 COVID-19 positive and 115 COVID-19 negative PCX images, the latter comprising roughly equally many pneumonia, emphysema, fibrosis, and healthy images (230 total images). Two common convolutional neural network architectures were used, VGG16 and DenseNet121, the former initially configured with off-the-shelf (OTS) parameters and the latter with either OTS or exclusively X-ray trained (XRT) parameters. The OTS parameters were derived from training on the ImageNet dataset, while the XRT parameters were obtained from training on the NIH chest X-ray dataset, ChestX-ray14. A final, densely connected layer was added to each model, the parameters of which were trained and validated on 87% of images from the experimental dataset, for the task of binary classification of images as COVID-19 positive or COVID-19 negative. Each model was tested on a hold-out set consisting of the other 13% of images. Performance metrics were calculated as the average over five random 80%-20% splits of the images into training and validation sets, respectively.

• Study Type: Observational
• Enrollment (Actual): 230

Contacts and Locations

Study Locations

• United States
  • California
    • Oakland, California, United States, 94612-2603
      • Dascena

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

115 COVID-19 single PCX images and 115 non COVID-19 single PCX images (230 images total), collected from 81 unique COVID-19 patients and 91 unique non COVID-19 patients.

Description

Inclusion Criteria:

• Single PCX images collected from patients over 18 years of age

Exclusion Criteria:

• CT scans composed of multiple concerted X-rays
• Single PCX images collected from patients under 18 years of age

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
COVID-19 Patients; Single posteroanterior (or "front-on") X-rays collected from COVID-19 patients	Device: CovX; Convolutional neural network for classification of COVID-19 from chest X-rays
Non COVID-19 Patients; Single posteroanterior (or "front-on") X-rays collected from subsets of non COVID-19 patients	Device: CovX; Convolutional neural network for classification of COVID-19 from chest X-rays

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Identification of COVID-19	Identification of COVID-19 infection from chest X-ray analysis	Through study completion, an average of 2 months

Collaborators and Investigators

• Sponsor: Dascena

Publications and helpful links

Helpful Links

• Related Info

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2020
• Primary Completion (Actual): April 17, 2020
• Study Completion (Actual): April 17, 2020

Study Registration Dates

• First Submitted: April 20, 2020
• First Submitted That Met QC Criteria: April 21, 2020
• First Posted (Actual): April 24, 2020

Study Record Updates

• Last Update Posted (Actual): April 24, 2020
• Last Update Submitted That Met QC Criteria: April 21, 2020
• Last Verified: April 1, 2020

More Information

Terms related to this study

• Keywords: machine learning; COVID-19; classification; X-ray; posteroanterior; convolutional neural network architectures
• Additional Relevant MeSH Terms: Coronavirus Infections; Coronaviridae Infections; Nidovirales Infections; RNA Virus Infections; Virus Diseases; Infections; Respiratory Tract Infections; Respiratory Tract Diseases; Pneumonia, Viral; Pneumonia; Lung Diseases; COVID-19
• Other Study ID Numbers: 04202002

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No