Cargando…
BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset
In this work we design an end-to-end deep learning architecture for predicting, on Chest X-rays images (CXR), a multi-regional score conveying the degree of lung compromise in COVID-19 patients. Such semi-quantitative scoring system, namely Brixia score, is applied in serial monitoring of such patie...
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/PMC8010334/ https://www.ncbi.nlm.nih.gov/pubmed/33862337 http://dx.doi.org/10.1016/j.media.2021.102046 |
_version_ | 1783673041682694144 |
---|---|
author | Signoroni, Alberto Savardi, Mattia Benini, Sergio Adami, Nicola Leonardi, Riccardo Gibellini, Paolo Vaccher, Filippo Ravanelli, Marco Borghesi, Andrea Maroldi, Roberto Farina, Davide |
author_facet | Signoroni, Alberto Savardi, Mattia Benini, Sergio Adami, Nicola Leonardi, Riccardo Gibellini, Paolo Vaccher, Filippo Ravanelli, Marco Borghesi, Andrea Maroldi, Roberto Farina, Davide |
author_sort | Signoroni, Alberto |
collection | PubMed |
description | In this work we design an end-to-end deep learning architecture for predicting, on Chest X-rays images (CXR), a multi-regional score conveying the degree of lung compromise in COVID-19 patients. Such semi-quantitative scoring system, namely Brixia score, is applied in serial monitoring of such patients, showing significant prognostic value, in one of the hospitals that experienced one of the highest pandemic peaks in Italy. To solve such a challenging visual task, we adopt a weakly supervised learning strategy structured to handle different tasks (segmentation, spatial alignment, and score estimation) trained with a “from-the-part-to-the-whole” procedure involving different datasets. In particular, we exploit a clinical dataset of almost 5,000 CXR annotated images collected in the same hospital. Our BS-Net demonstrates self-attentive behavior and a high degree of accuracy in all processing stages. Through inter-rater agreement tests and a gold standard comparison, we show that our solution outperforms single human annotators in rating accuracy and consistency, thus supporting the possibility of using this tool in contexts of computer-assisted monitoring. Highly resolved (super-pixel level) explainability maps are also generated, with an original technique, to visually help the understanding of the network activity on the lung areas. We also consider other scores proposed in literature and provide a comparison with a recently proposed non-specific approach. We eventually test the performance robustness of our model on an assorted public COVID-19 dataset, for which we also provide Brixia score annotations, observing good direct generalization and fine-tuning capabilities that highlight the portability of BS-Net in other clinical settings. The CXR dataset along with the source code and the trained model are publicly released for research purposes. |
format | Online Article Text |
id | pubmed-8010334 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier B.V. |
record_format | MEDLINE/PubMed |
spelling | pubmed-80103342021-03-31 BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset Signoroni, Alberto Savardi, Mattia Benini, Sergio Adami, Nicola Leonardi, Riccardo Gibellini, Paolo Vaccher, Filippo Ravanelli, Marco Borghesi, Andrea Maroldi, Roberto Farina, Davide Med Image Anal Article In this work we design an end-to-end deep learning architecture for predicting, on Chest X-rays images (CXR), a multi-regional score conveying the degree of lung compromise in COVID-19 patients. Such semi-quantitative scoring system, namely Brixia score, is applied in serial monitoring of such patients, showing significant prognostic value, in one of the hospitals that experienced one of the highest pandemic peaks in Italy. To solve such a challenging visual task, we adopt a weakly supervised learning strategy structured to handle different tasks (segmentation, spatial alignment, and score estimation) trained with a “from-the-part-to-the-whole” procedure involving different datasets. In particular, we exploit a clinical dataset of almost 5,000 CXR annotated images collected in the same hospital. Our BS-Net demonstrates self-attentive behavior and a high degree of accuracy in all processing stages. Through inter-rater agreement tests and a gold standard comparison, we show that our solution outperforms single human annotators in rating accuracy and consistency, thus supporting the possibility of using this tool in contexts of computer-assisted monitoring. Highly resolved (super-pixel level) explainability maps are also generated, with an original technique, to visually help the understanding of the network activity on the lung areas. We also consider other scores proposed in literature and provide a comparison with a recently proposed non-specific approach. We eventually test the performance robustness of our model on an assorted public COVID-19 dataset, for which we also provide Brixia score annotations, observing good direct generalization and fine-tuning capabilities that highlight the portability of BS-Net in other clinical settings. The CXR dataset along with the source code and the trained model are publicly released for research purposes. Elsevier B.V. 2021-07 2021-03-31 /pmc/articles/PMC8010334/ /pubmed/33862337 http://dx.doi.org/10.1016/j.media.2021.102046 Text en © 2021 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 Signoroni, Alberto Savardi, Mattia Benini, Sergio Adami, Nicola Leonardi, Riccardo Gibellini, Paolo Vaccher, Filippo Ravanelli, Marco Borghesi, Andrea Maroldi, Roberto Farina, Davide BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title | BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title_full | BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title_fullStr | BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title_full_unstemmed | BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title_short | BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset |
title_sort | bs-net: learning covid-19 pneumonia severity on a large chest x-ray dataset |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8010334/ https://www.ncbi.nlm.nih.gov/pubmed/33862337 http://dx.doi.org/10.1016/j.media.2021.102046 |
work_keys_str_mv | AT signoronialberto bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT savardimattia bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT beninisergio bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT adaminicola bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT leonardiriccardo bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT gibellinipaolo bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT vaccherfilippo bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT ravanellimarco bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT borghesiandrea bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT maroldiroberto bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset AT farinadavide bsnetlearningcovid19pneumoniaseverityonalargechestxraydataset |