Cargando…
New patch-based strategy for COVID-19 automatic identification using chest x-ray images
PURPOSE: The development of a robust model for automatic identification of COVID-19 based on chest x-rays has been a widely addressed topic over the last couple of years; however, the scarcity of good quality images sets, and their limited size, have proven to be an important obstacle to obtain reli...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647770/ https://www.ncbi.nlm.nih.gov/pubmed/36406188 http://dx.doi.org/10.1007/s12553-022-00704-4 |
_version_ | 1784827447230857216 |
---|---|
author | Portal-Diaz, Jorge A Lovelle-Enríquez, Orlando Perez-Diaz, Marlen Lopez-Cabrera, José D Reyes-Cardoso, Osmany Orozco-Morales, Ruben |
author_facet | Portal-Diaz, Jorge A Lovelle-Enríquez, Orlando Perez-Diaz, Marlen Lopez-Cabrera, José D Reyes-Cardoso, Osmany Orozco-Morales, Ruben |
author_sort | Portal-Diaz, Jorge A |
collection | PubMed |
description | PURPOSE: The development of a robust model for automatic identification of COVID-19 based on chest x-rays has been a widely addressed topic over the last couple of years; however, the scarcity of good quality images sets, and their limited size, have proven to be an important obstacle to obtain reliable models. In fact, models proposed so far have suffered from over-fitting erroneous features instead of learning lung features, a phenomenon known as shortcut learning. In this research, a new image classification methodology is proposed that attempts to mitigate this problem. METHODS: To this end, annotation by expert radiologists of a set of images was performed. The lung region was then segmented and a new classification strategy based on a patch partitioning that improves the resolution of the convolution neural network is proposed. In addition, a set of native images, used as an external evaluation set, is released. RESULTS: The best results were obtained for the 6-patch splitting variant with 0.887 accuracy, 0.85 recall and 0.848 F1score on the external validation set. CONCLUSION: The results show that the proposed new strategy maintains similar values between internal and external validation, which gives our model generalization power, making it available for use in hospital settings. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s12553-022-00704-4. |
format | Online Article Text |
id | pubmed-9647770 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-96477702022-11-14 New patch-based strategy for COVID-19 automatic identification using chest x-ray images Portal-Diaz, Jorge A Lovelle-Enríquez, Orlando Perez-Diaz, Marlen Lopez-Cabrera, José D Reyes-Cardoso, Osmany Orozco-Morales, Ruben Health Technol (Berl) Original Paper PURPOSE: The development of a robust model for automatic identification of COVID-19 based on chest x-rays has been a widely addressed topic over the last couple of years; however, the scarcity of good quality images sets, and their limited size, have proven to be an important obstacle to obtain reliable models. In fact, models proposed so far have suffered from over-fitting erroneous features instead of learning lung features, a phenomenon known as shortcut learning. In this research, a new image classification methodology is proposed that attempts to mitigate this problem. METHODS: To this end, annotation by expert radiologists of a set of images was performed. The lung region was then segmented and a new classification strategy based on a patch partitioning that improves the resolution of the convolution neural network is proposed. In addition, a set of native images, used as an external evaluation set, is released. RESULTS: The best results were obtained for the 6-patch splitting variant with 0.887 accuracy, 0.85 recall and 0.848 F1score on the external validation set. CONCLUSION: The results show that the proposed new strategy maintains similar values between internal and external validation, which gives our model generalization power, making it available for use in hospital settings. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s12553-022-00704-4. Springer Berlin Heidelberg 2022-11-10 2022 /pmc/articles/PMC9647770/ /pubmed/36406188 http://dx.doi.org/10.1007/s12553-022-00704-4 Text en © The Author(s) under exclusive licence to International Union for Physical and Engineering Sciences in Medicine (IUPESM) 2022, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Original Paper Portal-Diaz, Jorge A Lovelle-Enríquez, Orlando Perez-Diaz, Marlen Lopez-Cabrera, José D Reyes-Cardoso, Osmany Orozco-Morales, Ruben New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title | New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title_full | New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title_fullStr | New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title_full_unstemmed | New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title_short | New patch-based strategy for COVID-19 automatic identification using chest x-ray images |
title_sort | new patch-based strategy for covid-19 automatic identification using chest x-ray images |
topic | Original Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647770/ https://www.ncbi.nlm.nih.gov/pubmed/36406188 http://dx.doi.org/10.1007/s12553-022-00704-4 |
work_keys_str_mv | AT portaldiazjorgea newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages AT lovelleenriquezorlando newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages AT perezdiazmarlen newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages AT lopezcabrerajosed newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages AT reyescardosoosmany newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages AT orozcomoralesruben newpatchbasedstrategyforcovid19automaticidentificationusingchestxrayimages |