Cargando…
Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images
Accurate segmentation of infected lesions in chest images remains a challenging task due to the lack of utilization of lung region information, which could serve as a strong location hint for infection. In this paper, we propose a novel segmentation network Co-ERA-Net for infections in chest images...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451793/ https://www.ncbi.nlm.nih.gov/pubmed/37627813 http://dx.doi.org/10.3390/bioengineering10080928 |
_version_ | 1785095504526311424 |
---|---|
author | He, Zebang Wong, Alex Ngai Nick Yoo, Jung Sun |
author_facet | He, Zebang Wong, Alex Ngai Nick Yoo, Jung Sun |
author_sort | He, Zebang |
collection | PubMed |
description | Accurate segmentation of infected lesions in chest images remains a challenging task due to the lack of utilization of lung region information, which could serve as a strong location hint for infection. In this paper, we propose a novel segmentation network Co-ERA-Net for infections in chest images that leverages lung region information by enhancing supervised information and fusing multi-scale lung region and infection information at different levels. To achieve this, we introduce a Co-supervision scheme incorporating lung region information to guide the network to accurately locate infections within the lung region. Furthermore, we design an Enhanced Region Attention Module (ERAM) to highlight regions with a high probability of infection by incorporating infection information into the lung region information. The effectiveness of the proposed scheme is demonstrated using COVID-19 CT and X-ray datasets, with the results showing that the proposed schemes and modules are promising. Based on the baseline, the Co-supervision scheme, when integrated with lung region information, improves the Dice coefficient by 7.41% and 2.22%, and the IoU by 8.20% and 3.00% in CT and X-ray datasets respectively. Moreover, when this scheme is combined with the Enhanced Region Attention Module, the Dice coefficient sees further improvement of 14.24% and 2.97%, with the IoU increasing by 28.64% and 4.49% for the same datasets. In comparison with existing approaches across various datasets, our proposed method achieves better segmentation performance in all main metrics and exhibits the best generalization and comprehensive performance. |
format | Online Article Text |
id | pubmed-10451793 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-104517932023-08-26 Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images He, Zebang Wong, Alex Ngai Nick Yoo, Jung Sun Bioengineering (Basel) Article Accurate segmentation of infected lesions in chest images remains a challenging task due to the lack of utilization of lung region information, which could serve as a strong location hint for infection. In this paper, we propose a novel segmentation network Co-ERA-Net for infections in chest images that leverages lung region information by enhancing supervised information and fusing multi-scale lung region and infection information at different levels. To achieve this, we introduce a Co-supervision scheme incorporating lung region information to guide the network to accurately locate infections within the lung region. Furthermore, we design an Enhanced Region Attention Module (ERAM) to highlight regions with a high probability of infection by incorporating infection information into the lung region information. The effectiveness of the proposed scheme is demonstrated using COVID-19 CT and X-ray datasets, with the results showing that the proposed schemes and modules are promising. Based on the baseline, the Co-supervision scheme, when integrated with lung region information, improves the Dice coefficient by 7.41% and 2.22%, and the IoU by 8.20% and 3.00% in CT and X-ray datasets respectively. Moreover, when this scheme is combined with the Enhanced Region Attention Module, the Dice coefficient sees further improvement of 14.24% and 2.97%, with the IoU increasing by 28.64% and 4.49% for the same datasets. In comparison with existing approaches across various datasets, our proposed method achieves better segmentation performance in all main metrics and exhibits the best generalization and comprehensive performance. MDPI 2023-08-04 /pmc/articles/PMC10451793/ /pubmed/37627813 http://dx.doi.org/10.3390/bioengineering10080928 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article He, Zebang Wong, Alex Ngai Nick Yoo, Jung Sun Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title | Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title_full | Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title_fullStr | Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title_full_unstemmed | Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title_short | Co-ERA-Net: Co-Supervision and Enhanced Region Attention for Accurate Segmentation in COVID-19 Chest Infection Images |
title_sort | co-era-net: co-supervision and enhanced region attention for accurate segmentation in covid-19 chest infection images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451793/ https://www.ncbi.nlm.nih.gov/pubmed/37627813 http://dx.doi.org/10.3390/bioengineering10080928 |
work_keys_str_mv | AT hezebang coeranetcosupervisionandenhancedregionattentionforaccuratesegmentationincovid19chestinfectionimages AT wongalexngainick coeranetcosupervisionandenhancedregionattentionforaccuratesegmentationincovid19chestinfectionimages AT yoojungsun coeranetcosupervisionandenhancedregionattentionforaccuratesegmentationincovid19chestinfectionimages |