Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields
文献类型：期刊论文
| 作者 | Lin, Lei2,3,4,5; Garcia-Lorenzo, Daniel3,4,5; Li, Chong2,6 ; Jiang, Tianzi1; Barillot, Christian3,4,5
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2011-05-01 |
| 卷号 | 32期号:7页码:1036-1043 |
| 关键词 | MRI segmentation Markov random field Adaptive mean shift Pixon-representation EM algorithm |
| 英文摘要 | In this paper, we proposed an adaptive pixon represented segmentation (APRS) algorithm for 3D magnetic resonance (MR) brain images. Different from traditional method, an adaptive mean shift algorithm was adopted to adaptively smooth the query image and create a pixon-based image representation. Then K-means algorithm was employed to provide an initial segmentation by classifying the pixons in image into a predefined number of tissue classes. By using this segmentation as initialization, expectation-maximization (EM) iterations composed of bias correction, a priori digital brain atlas information, and Markov random field (MRF) segmentation were processed. Pixons were assigned with final labels when the algorithm converges. The adoption of bias correction and brain atlas made the current method more suitable for brain image segmentation than the previous pixon based segmentation algorithm. The proposed method was validated on both simulated normal brain images from BrainWeb and real brain images from the IBSR public dataset. Compared with some other popular MRI segmentation methods, the proposed method exhibited a higher degree of accuracy in segmenting both simulated and real 3D MRI brain data. The experimental results were numerically assessed using Dice and Tanimoto coefficients. (C) 2011 Elsevier B.V. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | MULTIPLE-SCLEROSIS LESIONS ; MAGNETIC-RESONANCE IMAGES ; TISSUE CLASSIFICATION ; CLUSTERING-ALGORITHM ; EDGE-DETECTION ; MODEL ; INFORMATION |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000290076800016 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3101]  |
| 专题 | 自动化研究所_脑网络组研究中心 |
| 作者单位 | 1.Chinese Acad Sci, LIAMA Ctr Computat Med, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Zhejiang Univ, Dept Math, Hangzhou 310027, Peoples R China 3.IRISA, INRIA, VisAGeS Unit Project, F-35042 Rennes, France 4.Univ Rennes 1, CNRS, IRISA, UMR 6074, F-35042 Rennes, France 5.IRISA, INSERM, INRIA, VisAGeS U746 Unit Project, F-35042 Rennes, France 6.King Saud Univ, Coll Sci, Dept Math, Riyadh 11451, Saudi Arabia |
| 推荐引用方式 GB/T 7714 | Lin, Lei,Garcia-Lorenzo, Daniel,Li, Chong,et al. Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields[J]. PATTERN RECOGNITION LETTERS,2011,32(7):1036-1043. |
| APA | Lin, Lei,Garcia-Lorenzo, Daniel,Li, Chong,Jiang, Tianzi,&Barillot, Christian.(2011).Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields.PATTERN RECOGNITION LETTERS,32(7),1036-1043. |
| MLA | Lin, Lei,et al."Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields".PATTERN RECOGNITION LETTERS 32.7(2011):1036-1043. |
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。