An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network
COVID-19 has spread rapidly across the world since late 2019. As of December, 2021, there are over 250 million documented COVID-19 cases and over 5 million deaths worldwide, which have caused businesses, schools, and government operations to shut down. The most common method of detecting COVID-19 is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/9/4/98 |
| _version_ | 1797500243619610624 |
|---|---|
| author | Gabriel Ackall Mohammed Elmzoudi Richard Yuan Cuixian Chen |
| author_facet | Gabriel Ackall Mohammed Elmzoudi Richard Yuan Cuixian Chen |
| author_sort | Gabriel Ackall |
| collection | DOAJ |
| description | COVID-19 has spread rapidly across the world since late 2019. As of December, 2021, there are over 250 million documented COVID-19 cases and over 5 million deaths worldwide, which have caused businesses, schools, and government operations to shut down. The most common method of detecting COVID-19 is the RT-PCR swab test, which suffers from a high false-negative rate and a very slow turnaround for results, often up to two weeks. Because of this, specialists often manually review X-ray images of the lungs to detect the presence of COVID-19 with up to 97% accuracy. Neural network algorithms greatly accelerate this review process, analyzing hundreds of X-rays in seconds. Using the Cohen COVID-19 X-ray Database and the NIH ChestX-ray8 Database, we trained and constructed the xRGM-NET convolutional neural network (CNN) to detect COVID-19 in X-ray scans of the lungs. To further aid medical professionals in the manual review of X-rays, we implemented the CNN activation mapping technique Score-CAM, which generates a heat map over an X-ray to illustrate which areas in the scan are most influential over the ultimate diagnosis. xRGM-NET achieved an overall classification accuracy of 97% with a sensitivity of 94% and specificity of 97%. Lightweight models like xRGM-NET can serve to improve the efficiency and accuracy of COVID-19 detection in developing countries or rural areas. In this paper, we report on our model and methods that were developed as part of a STEM enrichment summer program for high school students. We hope that our model and methods will allow other researchers to create lightweight and accurate models as more COVID-19 X-ray scans become available. |
| first_indexed | 2024-03-10T03:59:07Z |
| format | Article |
| id | doaj.art-8cdbd753a25240a8aba8b20b307ec8a2 |
| institution | Directory Open Access Journal |
| issn | 2227-7080 |
| language | English |
| last_indexed | 2024-03-10T03:59:07Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj.art-8cdbd753a25240a8aba8b20b307ec8a22023-11-23T10:48:21ZengMDPI AGTechnologies2227-70802021-12-01949810.3390/technologies9040098An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural NetworkGabriel Ackall0Mohammed Elmzoudi1Richard Yuan2Cuixian Chen3School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USADepartment of Computer Science, Duke University, Durham, NC 27708, USASchool of Humanities and Sciences, Stanford University, Stanford, CA 94305, USADepartment of Mathematics and Statistics, University of North Carolina Wilmington, Wilmington, NC 28407, USACOVID-19 has spread rapidly across the world since late 2019. As of December, 2021, there are over 250 million documented COVID-19 cases and over 5 million deaths worldwide, which have caused businesses, schools, and government operations to shut down. The most common method of detecting COVID-19 is the RT-PCR swab test, which suffers from a high false-negative rate and a very slow turnaround for results, often up to two weeks. Because of this, specialists often manually review X-ray images of the lungs to detect the presence of COVID-19 with up to 97% accuracy. Neural network algorithms greatly accelerate this review process, analyzing hundreds of X-rays in seconds. Using the Cohen COVID-19 X-ray Database and the NIH ChestX-ray8 Database, we trained and constructed the xRGM-NET convolutional neural network (CNN) to detect COVID-19 in X-ray scans of the lungs. To further aid medical professionals in the manual review of X-rays, we implemented the CNN activation mapping technique Score-CAM, which generates a heat map over an X-ray to illustrate which areas in the scan are most influential over the ultimate diagnosis. xRGM-NET achieved an overall classification accuracy of 97% with a sensitivity of 94% and specificity of 97%. Lightweight models like xRGM-NET can serve to improve the efficiency and accuracy of COVID-19 detection in developing countries or rural areas. In this paper, we report on our model and methods that were developed as part of a STEM enrichment summer program for high school students. We hope that our model and methods will allow other researchers to create lightweight and accurate models as more COVID-19 X-ray scans become available.https://www.mdpi.com/2227-7080/9/4/98COVID-19RT-PCR swab testconvolutional neural network (CNN)X-rayactivation mappingscore-CAM |
| spellingShingle | Gabriel Ackall Mohammed Elmzoudi Richard Yuan Cuixian Chen An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network Technologies COVID-19 RT-PCR swab test convolutional neural network (CNN) X-ray activation mapping score-CAM |
| title | An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network |
| title_full | An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network |
| title_fullStr | An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network |
| title_full_unstemmed | An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network |
| title_short | An Exploration into the Detection of COVID-19 from Chest X-ray Scans Using the xRGM-NET Convolutional Neural Network |
| title_sort | exploration into the detection of covid 19 from chest x ray scans using the xrgm net convolutional neural network |
| topic | COVID-19 RT-PCR swab test convolutional neural network (CNN) X-ray activation mapping score-CAM |
| url | https://www.mdpi.com/2227-7080/9/4/98 |
| work_keys_str_mv | AT gabrielackall anexplorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT mohammedelmzoudi anexplorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT richardyuan anexplorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT cuixianchen anexplorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT gabrielackall explorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT mohammedelmzoudi explorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT richardyuan explorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork AT cuixianchen explorationintothedetectionofcovid19fromchestxrayscansusingthexrgmnetconvolutionalneuralnetwork |