View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs
Locating lung field is a critical and fundamental processing stage in the automated analysis of chest radiographs (CXRs) for pulmonary disorders. During the routine examination of CXRs, using both frontal and lateral CXRs can benefit clinical diagnosis of cardiothoracic and lung diseases. However, t...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9406789/ |
id |
doaj-3c5fc9931ac244c7ab73db9bc0f38571 |
---|---|
record_format |
Article |
spelling |
doaj-3c5fc9931ac244c7ab73db9bc0f385712021-04-23T23:01:15ZengIEEEIEEE Access2169-35362021-01-019598355984710.1109/ACCESS.2021.30740269406789View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest RadiographsYuhua Xi0https://orcid.org/0000-0001-5435-0012Liming Zhong1https://orcid.org/0000-0002-0048-7838Weijie Xie2https://orcid.org/0000-0002-4024-3619Genggeng Qin3https://orcid.org/0000-0002-7563-3924Yunbi Liu4https://orcid.org/0000-0001-7260-3626Qianjin Feng5https://orcid.org/0000-0001-8647-0596Wei Yang6https://orcid.org/0000-0002-2161-3231School of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaDepartment of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaLocating lung field is a critical and fundamental processing stage in the automated analysis of chest radiographs (CXRs) for pulmonary disorders. During the routine examination of CXRs, using both frontal and lateral CXRs can benefit clinical diagnosis of cardiothoracic and lung diseases. However, the accurate segmentation of lung fields on both frontal and lateral CXRs is still challenging due to the blurry boundary of the lung field on lateral CXRs and the poor generalization ability of the models. Existing deep learning-based methods focused on lung field segmentation on frontal CXRs, and the generalization ability of these methods on the different type of CXRs (e.g., pediatric CXRs) and new lung diseases (e.g., COVID-19) has not been tested. In this paper, a view identification assisted fully convolutional network (VI-FCN) is proposed for the segmentation of lung fields on frontal and lateral CXRs simultaneously. The VI-FCN consists of an FCN branch for lung field segmentation and a view identification branch for identification of the frontal and lateral CXRs and for enhancing the lung field segmentation. To improve the generalization ability of VI-FCN, six public datasets and our frontal and lateral CXRs (over 2000 CXRs) were collected for training. The segmentation of lung fields on the Japanese Society of Radiological Technology (JSRT) dataset yields mean dice similarity coefficient (DSC) of 0.979 ± 0.008, mean Jaccard index (<inline-formula> <tex-math notation="LaTeX">$\Omega $ </tex-math></inline-formula>) of 0.959 ± 0.016, and mean boundary distance (MBD) of 1.023 ± 0.487 <italic>mm</italic>. Besides, the VI-FCN achieves mean DSC of 0.973 ± 0.010, mean <inline-formula> <tex-math notation="LaTeX">$\Omega $ </tex-math></inline-formula> of 0.947 ± 0.018, and mean MBD of 1.923 ± 0.755 <italic>mm</italic> for the segmentation of lung fields on our lateral CXRs. The experiments demonstrate the superior performance of the proposed VI-FCN over most of existing state-of-the-art methods. Moreover, the proposed VI-FCN achieves promising results on untrained pediatric CXRs and COVID-19 datasets.https://ieeexplore.ieee.org/document/9406789/Chest radiographslung field segmentationgeneralization abilityCOVID-19 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yuhua Xi Liming Zhong Weijie Xie Genggeng Qin Yunbi Liu Qianjin Feng Wei Yang |
spellingShingle |
Yuhua Xi Liming Zhong Weijie Xie Genggeng Qin Yunbi Liu Qianjin Feng Wei Yang View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs IEEE Access Chest radiographs lung field segmentation generalization ability COVID-19 |
author_facet |
Yuhua Xi Liming Zhong Weijie Xie Genggeng Qin Yunbi Liu Qianjin Feng Wei Yang |
author_sort |
Yuhua Xi |
title |
View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs |
title_short |
View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs |
title_full |
View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs |
title_fullStr |
View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs |
title_full_unstemmed |
View Identification Assisted Fully Convolutional Network for Lung Field Segmentation of Frontal and Lateral Chest Radiographs |
title_sort |
view identification assisted fully convolutional network for lung field segmentation of frontal and lateral chest radiographs |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
Locating lung field is a critical and fundamental processing stage in the automated analysis of chest radiographs (CXRs) for pulmonary disorders. During the routine examination of CXRs, using both frontal and lateral CXRs can benefit clinical diagnosis of cardiothoracic and lung diseases. However, the accurate segmentation of lung fields on both frontal and lateral CXRs is still challenging due to the blurry boundary of the lung field on lateral CXRs and the poor generalization ability of the models. Existing deep learning-based methods focused on lung field segmentation on frontal CXRs, and the generalization ability of these methods on the different type of CXRs (e.g., pediatric CXRs) and new lung diseases (e.g., COVID-19) has not been tested. In this paper, a view identification assisted fully convolutional network (VI-FCN) is proposed for the segmentation of lung fields on frontal and lateral CXRs simultaneously. The VI-FCN consists of an FCN branch for lung field segmentation and a view identification branch for identification of the frontal and lateral CXRs and for enhancing the lung field segmentation. To improve the generalization ability of VI-FCN, six public datasets and our frontal and lateral CXRs (over 2000 CXRs) were collected for training. The segmentation of lung fields on the Japanese Society of Radiological Technology (JSRT) dataset yields mean dice similarity coefficient (DSC) of 0.979 ± 0.008, mean Jaccard index (<inline-formula> <tex-math notation="LaTeX">$\Omega $ </tex-math></inline-formula>) of 0.959 ± 0.016, and mean boundary distance (MBD) of 1.023 ± 0.487 <italic>mm</italic>. Besides, the VI-FCN achieves mean DSC of 0.973 ± 0.010, mean <inline-formula> <tex-math notation="LaTeX">$\Omega $ </tex-math></inline-formula> of 0.947 ± 0.018, and mean MBD of 1.923 ± 0.755 <italic>mm</italic> for the segmentation of lung fields on our lateral CXRs. The experiments demonstrate the superior performance of the proposed VI-FCN over most of existing state-of-the-art methods. Moreover, the proposed VI-FCN achieves promising results on untrained pediatric CXRs and COVID-19 datasets. |
topic |
Chest radiographs lung field segmentation generalization ability COVID-19 |
url |
https://ieeexplore.ieee.org/document/9406789/ |
work_keys_str_mv |
AT yuhuaxi viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT limingzhong viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT weijiexie viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT genggengqin viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT yunbiliu viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT qianjinfeng viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs AT weiyang viewidentificationassistedfullyconvolutionalnetworkforlungfieldsegmentationoffrontalandlateralchestradiographs |
_version_ |
1714660960811089920 |