Local Label Learning (LLL) for Subcortical Structure Segmentation: Application to Hippocampus Segmentation

	Local Label Learning (LLL) for Subcortical Structure Segmentation: Application to Hippocampus Segmentation
	Hao, Yongfu 1; Wang, Tianyao 2; Zhang, Xinqing 3; Duan, Yunyun 4; Yu, Chunshui 5; Jiang, Tianzi1 ; Fan, Yong 1; Alzheimer's Dis Neuroimaging
发表期刊	HUMAN BRAIN MAPPING
	2014-06-01
卷号	35 期号:6 页码:2674-2697
文章类型	Article
摘要	Automatic and reliable segmentation of subcortical structures is an important but difficult task in quantitative brain image analysis. Multi-atlas based segmentation methods have attracted great interest due to their promising performance. Under the multi-atlas based segmentation framework, using deformation fields generated for registering atlas images onto a target image to be segmented, labels of the atlases are first propagated to the target image space and then fused to get the target image segmentation based on a label fusion strategy. While many label fusion strategies have been developed, most of these methods adopt predefined weighting models that are not necessarily optimal. In this study, we propose a novel local label learning strategy to estimate the target image's segmentation label using statistical machine learning techniques. In particular, we use a L1-regularized support vector machine (SVM) with a k nearest neighbor (kNN) based training sample selection strategy to learn a classifier for each of the target image voxel from its neighboring voxels in the atlases based on both image intensity and texture features. Our method has produced segmentation results consistently better than state-of-the-art label fusion methods in validation experiments on hippocampal segmentation of over 100 MR images obtained from publicly available and in-house datasets. Volumetric analysis has also demonstrated the capability of our method in detecting hippocampal volume changes due to Alzheimer's disease. Hum Brain Mapp 35:2674-2697, 2014. (c) 2013 Wiley Periodicals, Inc.
关键词	Multi-atlas Based Segmentation Local Label Learning Hippocampal Segmentation Svm
WOS标题词	Science & Technology ; Life Sciences & Biomedicine
关键词[WOS]	ATLAS-BASED SEGMENTATION ; WHOLE-BRAIN SEGMENTATION ; IMAGE SEGMENTATION ; ALZHEIMERS-DISEASE ; AUTOMATIC SEGMENTATION ; LINEAR CLASSIFICATION ; SELECTION-STRATEGIES ; REGISTRATION ; MRI ; FUSION
收录类别	SCI
语种	英语
WOS研究方向	Neurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Neurosciences ; Neuroimaging ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000334555100015
引用统计	被引频次：91[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/3149
专题	脑图谱与类脑智能实验室_脑网络组研究
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Brainnetome Ctr, Beijing 100190, Peoples R China 2.Shanghai East Hosp, Dept Radiol, Shanghai, Peoples R China 3.Capital Med Univ, Xuanwu Hosp, Dept Neurol, Beijing, Peoples R China 4.Capital Med Univ, Xuanwu Hosp, Dept Radiol, Beijing, Peoples R China 5.Tianjin Med Univ, Gen Hosp, Dept Radiol, Tianjin, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hao, Yongfu,Wang, Tianyao,Zhang, Xinqing,et al. Local Label Learning (LLL) for Subcortical Structure Segmentation: Application to Hippocampus Segmentation[J]. HUMAN BRAIN MAPPING,2014,35(6):2674-2697.
APA	Hao, Yongfu.,Wang, Tianyao.,Zhang, Xinqing.,Duan, Yunyun.,Yu, Chunshui.,...&Alzheimer's Dis Neuroimaging.(2014).Local Label Learning (LLL) for Subcortical Structure Segmentation: Application to Hippocampus Segmentation.HUMAN BRAIN MAPPING,35(6),2674-2697.
MLA	Hao, Yongfu,et al."Local Label Learning (LLL) for Subcortical Structure Segmentation: Application to Hippocampus Segmentation".HUMAN BRAIN MAPPING 35.6(2014):2674-2697.