Development of lung segmentation method in x-ray images of children based on TransResUNet.

Frontiers in radiology Pub Date : 2023-01-01 DOI:10.3389/fradi.2023.1190745

Lingdong Chen, Zhuo Yu, Jian Huang, Liqi Shu, Pekka Kuosmanen, Chen Shen, Xiaohui Ma, Jing Li, Chensheng Sun, Zheming Li, Ting Shu, Gang Yu

{"title":"Development of lung segmentation method in x-ray images of children based on TransResUNet.","authors":"Lingdong Chen, Zhuo Yu, Jian Huang, Liqi Shu, Pekka Kuosmanen, Chen Shen, Xiaohui Ma, Jing Li, Chensheng Sun, Zheming Li, Ting Shu, Gang Yu","doi":"10.3389/fradi.2023.1190745","DOIUrl":null,"url":null,"abstract":"Background: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.Objective: In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.Methods: The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.Results: Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.Conclusions: This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365102/pdf/","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in radiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fradi.2023.1190745","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

Background: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.

Objective: In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.

Methods: The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.

Results: Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.

Conclusions: This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Abstract Image

查看原文本刊更多论文

基于TransResUNet的儿童x射线图像肺部分割方法的研究。

背景:胸部x线(CXR)被广泛应用于儿童肺部疾病的检测和诊断。数字CXR图像的肺野分割是许多计算机辅助诊断系统的关键部分。目的:在本研究中，我们提出了一种基于深度学习的方法来提高儿童多中心CXR图像的肺分割质量和准确性。方法:该方法的新颖之处在于结合了TransUNet和ResUNet的优点。前者可以提供自关注模块，提高模型的特征学习能力，后者可以避免网络退化问题。结果:应用于包含多中心数据的测试集，我们的模型获得了0.9822的Dice得分。结论:本文提出的基于TransResUNet的肺图像分割方法优于现有的其他医学图像分割网络。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Frontiers in radiology

CiteScore

1.20

自引率

0.00%

发文量