A shape-guided deep residual network for automated CT lung segmentation
文献类型:期刊论文
作者 | Yang, Lei2,3; Gu, Yuge2,3; Huo, Benyan2,3; Liu, Yanhong2,3; Bian, Guibin1,3 |
刊名 | KNOWLEDGE-BASED SYSTEMS |
出版日期 | 2022-08-17 |
卷号 | 250页码:10 |
ISSN号 | 0950-7051 |
关键词 | Deep network architecture Medical image analysis Shape stream network Residual unit Attention fusion unit |
DOI | 10.1016/j.knosys.2022.108981 |
通讯作者 | Huo, Benyan(huoby@zzu.edu.cn) ; Liu, Yanhong(liuyh@zzu.edu.cn) |
英文摘要 | Automatic lung segmentation is an effective method for the precise computer-aided diagnosis of lung diseases. However, CT lung scans are always complex due to issues such as weak texture, poor contrast, and variation of appearances and positions, which will affect the lung segmentation accuracy. Recently, due to strong feature expression ability, many deep convolution neural networks (DCNNs) have been proposed for application in medical image segmentation to provide an end-to-end segmentation scheme, especially the U-shape network (U-Net) and its variants. However, accurate lung segmentation methods based on DCNNs still face a certain challenge because of the insufficient process of boundary information, restricted receptive field, etc. To address these issues, with the encoder-decoder framework, a novel shape-guided deep residual network is proposed in this paper for automatic CT lung segmentation. The proposed network is composed of two stream networks: the main stream network and the shape stream network. An effective deep attention residual network is built to act as the mainstream network for lung segmentation. Meanwhile, an attention fusion block is proposed to embed into the mainstream network for multiscale feature extraction of local feature maps. Based on the mainstream network, a shape stream network is proposed to serve as significant guidance for the mainstream network to accurately compute lung shape boundaries. Multiple public CT lung image sets are adopted to qualitatively and quantitatively analyze the segmentation performance on CT scans. Experimental results indicate that the proposed shape-guided deep residual network outperforms related advanced image segmentation methods on medical image analysis. (C) 2022 Elsevier B.V. All rights reserved. |
WOS关键词 | CHEST RADIOGRAPHS ; U-NET ; IMAGE |
资助项目 | National Key Research & Development Project of China[2020YFB1313701] ; National Natural Science Foundation of China[62003309] ; Outstanding Foreign Scientist Support Project in Henan Province of China[GZS2019008] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000833283600014 |
资助机构 | National Key Research & Development Project of China ; National Natural Science Foundation of China ; Outstanding Foreign Scientist Support Project in Henan Province of China |
源URL | [http://ir.ia.ac.cn/handle/173211/49833] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Huo, Benyan; Liu, Yanhong |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Robot Percept & Control Engn Lab, Zhengzhou 450001, Henan, Peoples R China 3.Zhengzhou Univ, Sch Elect Engn, Zhengzhou 450001, Henan, Peoples R China |
推荐引用方式 GB/T 7714 | Yang, Lei,Gu, Yuge,Huo, Benyan,et al. A shape-guided deep residual network for automated CT lung segmentation[J]. KNOWLEDGE-BASED SYSTEMS,2022,250:10. |
APA | Yang, Lei,Gu, Yuge,Huo, Benyan,Liu, Yanhong,&Bian, Guibin.(2022).A shape-guided deep residual network for automated CT lung segmentation.KNOWLEDGE-BASED SYSTEMS,250,10. |
MLA | Yang, Lei,et al."A shape-guided deep residual network for automated CT lung segmentation".KNOWLEDGE-BASED SYSTEMS 250(2022):10. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。