CeLNet: a correlation-enhanced lightweight network for medical image segmentation
文献类型:期刊论文
作者 | Zhang, Bangze1; Wang, Xiaoyan1; Liu, Lianggui4; Zhang, Denghui4; Huang, Xiaojie3; Xia, Ming1; Jiang, Weiwei1; Huang, Xiangsheng2 |
刊名 | PHYSICS IN MEDICINE AND BIOLOGY |
出版日期 | 2023-06-07 |
卷号 | 68期号:11页码:14 |
ISSN号 | 0031-9155 |
关键词 | medical image multi-slice segmentation lightweight contextual learning |
DOI | 10.1088/1361-6560/acd519 |
通讯作者 | Wang, Xiaoyan(xiaoyanwang@zjut.edu.cn) |
英文摘要 | Objective. Convolutional neural networks have been widely adopted for medical image segmentation with their outstanding feature representation capabilities. As the segmentation accuracy gets constantly updated, the complexity of networks increases as well. Complex networks can achieve better performance but require more parameters and are hard to train with limited resources, while lightweight models are faster but cannot fully utilize the contextual information of medical images. In this paper, we focus on better balancing the efficiency and accuracy. Approach. We propose a correlation-enhanced lightweight network (CeLNet) for medical image segmentation, which adopts a siamese structure for weight sharing and parameter saving. Through the feature reuse and feature stacking of parallel branches, a point-depth convolution parallel block (PDP Block) is proposed to reduce the model parameters and computational cost while improving the feature extraction capability of encoder. A relation module is also designed to extract feature correlations of input slices, which utilizes global and local attention to enhance feature connections, while reducing feature differences through element subtraction, and finally obtains contextual information of associated slices to improve the segmentation performance. Main results. We conduct extensive experiments on the LiTS2017, MM-WHS and ISIC2018 datasets, and the proposed model consumes merely 5.18M parameters but achieves excellent segmentation performance, specifically, a DSC of 0.9233 in LiTS2017 dataset, an average DSC of 0.7895 on MM-WHS dataset and an average DSC of 0.8401 on ISIC2018 dataset. Significance. CeLNet achieves state-of-the-art performance in multiple datasets while ensuring lightweight. |
资助项目 | Zhejiang Provincial Natural Science Foundation of China[LY23F030007] ; Zhejiang Provincial Natural Science Foundation of China[LQ20H160052] ; Zhejiang Provincial Natural Science Foundation of China[LY20H180006] ; National Natural Science Foundation of China[62273308] ; National Natural Science Foundation of China[61701442] ; Zhejiang Provincial Research Project on the Application of Public Welfare Technologies[LGF22F020023] ; National Key R&D Program of China[2020YFC2006406] |
WOS研究方向 | Engineering ; Radiology, Nuclear Medicine & Medical Imaging |
语种 | 英语 |
出版者 | IOP Publishing Ltd |
WOS记录号 | WOS:000997151200001 |
资助机构 | Zhejiang Provincial Natural Science Foundation of China ; National Natural Science Foundation of China ; Zhejiang Provincial Research Project on the Application of Public Welfare Technologies ; National Key R&D Program of China |
源URL | [http://ir.ia.ac.cn/handle/173211/53399] |
专题 | 融合创新中心_决策指挥与体系智能 |
通讯作者 | Wang, Xiaoyan |
作者单位 | 1.Zhejiang Univ Technol, Sch Comp Sci & Technol, Hangzhou 310023, Zhejiang, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Zhejiang Univ, Affiliated Hosp 2, Sch Med, Hangzhou 310009, Peoples R China 4.Zhejiang Shuren Univ, Coll Informat & Technol, Hangzhou 310015, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Bangze,Wang, Xiaoyan,Liu, Lianggui,et al. CeLNet: a correlation-enhanced lightweight network for medical image segmentation[J]. PHYSICS IN MEDICINE AND BIOLOGY,2023,68(11):14. |
APA | Zhang, Bangze.,Wang, Xiaoyan.,Liu, Lianggui.,Zhang, Denghui.,Huang, Xiaojie.,...&Huang, Xiangsheng.(2023).CeLNet: a correlation-enhanced lightweight network for medical image segmentation.PHYSICS IN MEDICINE AND BIOLOGY,68(11),14. |
MLA | Zhang, Bangze,et al."CeLNet: a correlation-enhanced lightweight network for medical image segmentation".PHYSICS IN MEDICINE AND BIOLOGY 68.11(2023):14. |
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。