Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images

doi:10.1002/mp.14585

	Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images
	Liu, Tianyu1 ; Liu, Junchi 2; Ma, Yan 1; He, Jiangping1 ; Han, Jincang1 ; Ding, Xiaoyang1 ; Chen, Chin-Tu 3
	2021-01
发表期刊	MEDICAL PHYSICS
卷号	48 期号:1 页码:264-272
摘要	Purpose The accurate segmentation of liver and liver tumors from CT images can assist radiologists in decision-making and treatment planning. The contours of liver and liver tumors are currently obtained by manual labeling, which is time-consuming and subjective. Computer-aided segmentation methods have been widely used in the segmentation of liver and liver tumors. However, due to the diversity of shape, volume, and image intensity, the segmentation is still a difficult task. In this study, we present a Spatial Feature Fusion Convolutional Network (SFF-Net) to automatically segment liver and liver tumors from CT images. Methods First, we extract side-outputs at each convolutional block in SFF-Net to make full use of multiscale features. Second, skip-connections are added in the down-sampling phase, therefore, the spatial information can be efficiently transferred to later layers. Third, we present feature fusion blocks (FFBs) to merge spatial features and high-level semantic features from early layers and later layers, respectively. Finally, a fully connected 3D conditional random fields (CRFs) is applied to refine the liver and liver tumor segmentation results. Results We test our method on the MICCAI 2017 Liver Tumor Segmentation (LiTS) challenge dataset. The Dice Global (DG) score, Dice per case (DC) score, Volume Overlap Error (VOE), Average Symmetric Surface Distance (ASSD), and tumor precision score are calculated to evaluate the liver and liver tumor segmentation accuracies. For the liver segmentation, DG is 0.955; DC is 0.937; VOE is 0.106; and ASSD is 3.678. For the tumor segmentation, DG is 0.746; DC is 0.592; VOE is 0.416; ASSD is 1.585 and the tumor precision score is 0.369. Conclusions The SFF-Net learns more spatial information by adding skip-connections and feature fusion blocks. The experiments validate that our method can accurately segment liver and liver tumors from CT images.
关键词	automatic segmentation CT images feature fusion liver liver tumor spatial information
DOI	10.1002/mp.14585
收录类别	EI ; SCOPUS ; SCIE
ISSN	0094-2405
语种	英语
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000592908400001
出版者	WILEY
EI入藏号	20204909562907
EI主题词	Convolution
EI分类号	461.2 Biological Materials and Tissue Engineering ; 716.1 Information Theory and Signal Processing ; 723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence ; 723.5 Computer Applications ; 912.2 Management ; 922.2 Mathematical Statistics
原始文献类型	Journal article (JA)
EISSN	2473-4209
引用统计	被引频次：36[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/21307
专题	信息工程与人工智能学院工商管理学院党委研究生工作部(学位管理与研究生工作处) 科技处学校办公室
通讯作者	He, Jiangping
作者单位	1.Lanzhou Univ Finance & Econ, Dept Elect Engn, Lanzhou 730020, Peoples R China; 2.IIT, Dept Elect & Comp Engn, Chicago, IL 60616 USA; 3.Univ Chicago, Dept Radiol, Chicago, IL 60637 USA
第一作者单位	兰州财经大学
通讯作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Liu, Tianyu,Liu, Junchi,Ma, Yan,et al. Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images[J]. MEDICAL PHYSICS,2021,48(1):264-272.
APA	Liu, Tianyu.,Liu, Junchi.,Ma, Yan.,He, Jiangping.,Han, Jincang.,...&Chen, Chin-Tu.(2021).Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images.MEDICAL PHYSICS,48(1),264-272.
MLA	Liu, Tianyu,et al."Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images".MEDICAL PHYSICS 48.1(2021):264-272.