MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation
文献类型:期刊论文
作者 | Su, Run2,3; Zhang, Deyun1; Liu, Jinhuai2,3; Cheng, Chuandong4,5,6 |
刊名 | FRONTIERS IN GENETICS |
出版日期 | 2021-02-11 |
卷号 | 12 |
关键词 | multi-scale block U-net medical image segmentation convolution kernel receptive field |
DOI | 10.3389/fgene.2021.639930 |
通讯作者 | Liu, Jinhuai(jhliu@iim.ac.cn) |
英文摘要 | Aiming at the limitation of the convolution kernel with a fixed receptive field and unknown prior to optimal network width in U-Net, multi-scale U-Net (MSU-Net) is proposed by us for medical image segmentation. First, multiple convolution sequence is used to extract more semantic features from the images. Second, the convolution kernel with different receptive fields is used to make features more diverse. The problem of unknown network width is alleviated by efficient integration of convolution kernel with different receptive fields. In addition, the multi-scale block is extended to other variants of the original U-Net to verify its universality. Five different medical image segmentation datasets are used to evaluate MSU-Net. A variety of imaging modalities are included in these datasets, such as electron microscopy, dermoscope, ultrasound, etc. Intersection over Union (IoU) of MSU-Net on each dataset are 0.771, 0.867, 0.708, 0.900, and 0.702, respectively. Experimental results show that MSU-Net achieves the best performance on different datasets. Our implementation is available at https://github.com/CN-zdy/MSU_Net.. |
资助项目 | National Natural Science Foundation of China[62033002] ; Science and Technology Project grant from Anhui Province[1508085QHl84] ; Science and Technology Project grant from Anhui Province[201904a07020098] ; Fundamental Research Fund for the Central Universities[WK 9110000032] |
WOS研究方向 | Genetics & Heredity |
语种 | 英语 |
出版者 | FRONTIERS MEDIA SA |
WOS记录号 | WOS:000621359800001 |
资助机构 | National Natural Science Foundation of China ; Science and Technology Project grant from Anhui Province ; Fundamental Research Fund for the Central Universities |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/120161] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Liu, Jinhuai |
作者单位 | 1.Anhui Agr Univ, Sch Engn, Hefei, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Intelligent Machines, Hefei, Peoples R China 3.Univ Sci & Technol China, Grad Sch, Sci Isl Branch, Hefei, Peoples R China 4.Univ Sci & Technol China USTC, Affiliated Hosp 1, Dept Neurosurg, Hefei, Peoples R China 5.Univ Sci & Technol China, Div Life Sci & Med, Hefei, Peoples R China 6.Anhui Prov Key Lab Brain Funct & Brain Dis, Hefei, Peoples R China |
推荐引用方式 GB/T 7714 | Su, Run,Zhang, Deyun,Liu, Jinhuai,et al. MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation[J]. FRONTIERS IN GENETICS,2021,12. |
APA | Su, Run,Zhang, Deyun,Liu, Jinhuai,&Cheng, Chuandong.(2021).MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation.FRONTIERS IN GENETICS,12. |
MLA | Su, Run,et al."MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation".FRONTIERS IN GENETICS 12(2021). |
入库方式: OAI收割
来源:合肥物质科学研究院
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。