Frontiers in Radiology (Apr 2023)
Development of lung segmentation method in x-ray images of children based on TransResUNet
- Lingdong Chen,
- Lingdong Chen,
- Lingdong Chen,
- Zhuo Yu,
- Jian Huang,
- Jian Huang,
- Jian Huang,
- Liqi Shu,
- Pekka Kuosmanen,
- Pekka Kuosmanen,
- Chen Shen,
- Chen Shen,
- Chen Shen,
- Xiaohui Ma,
- Jing Li,
- Jing Li,
- Jing Li,
- Chensheng Sun,
- Chensheng Sun,
- Chensheng Sun,
- Zheming Li,
- Zheming Li,
- Zheming Li,
- Ting Shu,
- Gang Yu,
- Gang Yu,
- Gang Yu,
- Gang Yu
Affiliations
- Lingdong Chen
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Lingdong Chen
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Lingdong Chen
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Zhuo Yu
- Department of Scientific Research, Huiying Medical Technology (Beijing) Co., Ltd, Beijing, China
- Jian Huang
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Jian Huang
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Jian Huang
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Liqi Shu
- Department of Neurology, The Warren Alpert Medical School of Brown University, Providence, RI, United States
- Pekka Kuosmanen
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Pekka Kuosmanen
- Department of Scientific Research, Avaintec Oy Company, Helsinki, Finland
- Chen Shen
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Chen Shen
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Chen Shen
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Xiaohui Ma
- Department of Radiology, Children’s Hospital, Zhejiang University School of Medicine, Hangzhou, China
- Jing Li
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Jing Li
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Jing Li
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Chensheng Sun
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Chensheng Sun
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Chensheng Sun
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Zheming Li
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Zheming Li
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Zheming Li
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Ting Shu
- Department of Information Standardization Research,National Institute of Hospital Administration, NHC, Beijing, China
- Gang Yu
- Department of Data and Information, The Children’s Hospital Zhejiang University School of Medicine, Hangzhou, China
- Gang Yu
- Medicine Engineering and Information Research Institute for Children's Health, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China
- Gang Yu
- Medicine Engineering and Information Research Institute for Children's Health, National Clinical Research Center for Child Health, Hangzhou, China
- Gang Yu
- Polytechnic Institute, Zhejiang University, Hangzhou, China
- DOI
- https://doi.org/10.3389/fradi.2023.1190745
- Journal volume & issue
-
Vol. 3
Abstract
BackgroundChest 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.ObjectiveIn 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.MethodsThe 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.ResultsApplied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.ConclusionsThis novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.
Keywords
