Cargando…
Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN
COVID-19 is a deadly viral infection that has brought a significant threat to human lives. Automatic diagnosis of COVID-19 from medical imaging enables precise medication, helps to control community outbreak, and reinforces coronavirus testing methods in place. While there exist several challenges i...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier B.V.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7510455/ https://www.ncbi.nlm.nih.gov/pubmed/32989379 http://dx.doi.org/10.1016/j.asoc.2020.106744 |
_version_ | 1783585791358795776 |
---|---|
author | Karthik, R. Menaka, R. M., Hariharan |
author_facet | Karthik, R. Menaka, R. M., Hariharan |
author_sort | Karthik, R. |
collection | PubMed |
description | COVID-19 is a deadly viral infection that has brought a significant threat to human lives. Automatic diagnosis of COVID-19 from medical imaging enables precise medication, helps to control community outbreak, and reinforces coronavirus testing methods in place. While there exist several challenges in manually inferring traces of this viral infection from X-ray, Convolutional Neural Network (CNN) can mine data patterns that capture subtle distinctions between infected and normal X-rays. To enable automated learning of such latent features, a custom CNN architecture has been proposed in this research. It learns unique convolutional filter patterns for each kind of pneumonia. This is achieved by restricting certain filters in a convolutional layer to maximally respond only to a particular class of pneumonia/COVID-19. The CNN architecture integrates different convolution types to aid better context for learning robust features and strengthen gradient flow between layers. The proposed work also visualizes regions of saliency on the X-ray that have had the most influence on CNN’s prediction outcome. To the best of our knowledge, this is the first attempt in deep learning to learn custom filters within a single convolutional layer for identifying specific pneumonia classes. Experimental results demonstrate that the proposed work has significant potential in augmenting current testing methods for COVID-19. It achieves an F1-score of 97.20% and an accuracy of 99.80% on the COVID-19 X-ray set. |
format | Online Article Text |
id | pubmed-7510455 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier B.V. |
record_format | MEDLINE/PubMed |
spelling | pubmed-75104552020-09-24 Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN Karthik, R. Menaka, R. M., Hariharan Appl Soft Comput Article COVID-19 is a deadly viral infection that has brought a significant threat to human lives. Automatic diagnosis of COVID-19 from medical imaging enables precise medication, helps to control community outbreak, and reinforces coronavirus testing methods in place. While there exist several challenges in manually inferring traces of this viral infection from X-ray, Convolutional Neural Network (CNN) can mine data patterns that capture subtle distinctions between infected and normal X-rays. To enable automated learning of such latent features, a custom CNN architecture has been proposed in this research. It learns unique convolutional filter patterns for each kind of pneumonia. This is achieved by restricting certain filters in a convolutional layer to maximally respond only to a particular class of pneumonia/COVID-19. The CNN architecture integrates different convolution types to aid better context for learning robust features and strengthen gradient flow between layers. The proposed work also visualizes regions of saliency on the X-ray that have had the most influence on CNN’s prediction outcome. To the best of our knowledge, this is the first attempt in deep learning to learn custom filters within a single convolutional layer for identifying specific pneumonia classes. Experimental results demonstrate that the proposed work has significant potential in augmenting current testing methods for COVID-19. It achieves an F1-score of 97.20% and an accuracy of 99.80% on the COVID-19 X-ray set. Elsevier B.V. 2021-02 2020-09-23 /pmc/articles/PMC7510455/ /pubmed/32989379 http://dx.doi.org/10.1016/j.asoc.2020.106744 Text en © 2020 Elsevier B.V. All rights reserved. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active. |
spellingShingle | Article Karthik, R. Menaka, R. M., Hariharan Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title | Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title_full | Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title_fullStr | Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title_full_unstemmed | Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title_short | Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN |
title_sort | learning distinctive filters for covid-19 detection from chest x-ray using shuffled residual cnn |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7510455/ https://www.ncbi.nlm.nih.gov/pubmed/32989379 http://dx.doi.org/10.1016/j.asoc.2020.106744 |
work_keys_str_mv | AT karthikr learningdistinctivefiltersforcovid19detectionfromchestxrayusingshuffledresidualcnn AT menakar learningdistinctivefiltersforcovid19detectionfromchestxrayusingshuffledresidualcnn AT mhariharan learningdistinctivefiltersforcovid19detectionfromchestxrayusingshuffledresidualcnn |