北京生物醫(yī)學工程

一種基于模糊核聚類的腦部磁共振圖像分割算法

An algorithm for MRI brain image segmentation based on fuzzy kernel clustering

作者：相艷賀建峰易三莉徐家萍張嫻文

單位：昆明理工大學信息工程與自動化學院(昆明650500)

分類號：

出版年·卷·期（頁碼）：2013·32·5（515-518）

摘要：

目的針對普通模糊核聚類算法(kernel fuzzy c-means clustering algorithm，KFCM)存在的隨機選擇初始聚類中心的問題，本文提出一種根據(jù)直方圖得到確定的初始聚類中心的模糊核聚類算法，以更快速地分割腦部磁共振圖像。方法首先利用區(qū)域生長法和形態(tài)學方法對原始腦部磁共振圖像進行預處理，提取腦實質(zhì)，然后計算出預處理圖像的直方圖，將直方圖的4個峰值作為模糊核聚類的初始聚類中心，最后利用模糊核聚類算法對腦實質(zhì)進行分割。結(jié)果本文算法能有效地提取出腦組織中的白質(zhì)(white matter，WM)、灰質(zhì)(grey matter，GM)和腦脊髓液(cerebral spinal fluid，CSF)。與普通模糊核聚類算法相比，該算法的目標函數(shù)能更快地達到平穩(wěn)，從而縮短運行時間。結(jié)論本文算法與隨機選擇聚類中心的模糊核聚類算法相比，可減少迭代次數(shù)，更快地得到分割結(jié)果。

Objective To improve the random choice problem of the preliminary clustering centers in ordinary kernel fuzzy C-means clustering algorithm (KFCM)，this paper proposes a method which could get assured preliminary clustering centers according to histogram and segment MRI brain image quickly.Methods Firstly the original image was processed by using the region growing and the mathematical morphology techniques and brain parenchyma was extracted.Then the histogram of the pre-segmented image was calculated and the four recognized histogram peaks were chosen as the preliminary clustering centers of KFCM.Finally KFCM was applied to segment the brain parenchyma.Results The proposed method could abstract the white matter (WM)，gray matter (GM) and cerebral spinal fluid (CSF) from the brain image efficiently.The objective function of the proposed method tended to be steady more quickly than ordinary KFCM and the running time was shorter.Conclusions This proposed method can reduce the iteration numbers and quickly get segmentation results compared with the random choice centre of KFCM.

參考文獻：

［1］Bezdek JC.Pattern recognition with fuzzy objective function algorithms［M］.Boston: Kluwer Academic Publishers，1981.
［2］張莉，周偉達，焦李成.核聚類算法［J］.計算機學報，2002，25(6)：587-590.
Zhang Li，Zhou Weida，Jiao Licheng.Kernel clustering algorithm［J］.Chinese Journal of Computers，2002，25(6)：587-590.
［3］余學飛，李彬，陳武凡.基于模糊核聚類的MR圖像分割新算法［J］.南方醫(yī)科大學學報，2008，28(4)：555-557.
Yu Xuefei，Li Bin，Chen Wufan.A new algorithm for magnetic resonance image segmentation based on fuzzy kernel clustering［J］.Journal of South Medicine University，2008,28(4):555-557.
［4］Liao L，Lin T，Li B.MRI brain image segmentation and bias field correction based on fast spatially constrained kernel clustering approach［J］.Pattern Recognition Letters，2008，29:1580-1588.
［5］Yan MS，Tsai HS.A Gaussian kernel-based fuzzy c-means algorithm with a spatial bias correction［J］.Pattern Recognition Letters，2008，29(12): 1713-1725.
［6］Liu，C.and Zhang，X.Gaussian kernelized fuzzy c-means with spatial information algorithm for image segmentation［J］.Journal of Computers，2012，7(6): 1511-1518.
［7］沙秀艷，辛杰.基于最大熵的模糊核聚類圖像分割方法［J］.計算機工程，2011，37(10)：187-191.
Sha Xiuyan，Xin Jie.Fuzzy kernel clustering image segmentation method based on maximum entropy［J］.Computer Engineering，2011，37(10)：187-191.
［8］駱娜琴，鄧振生 .一種磁共振腦組織及腫瘤區(qū)域的提取方法［J］.北京生物醫(yī)學工程，2011，30（1）：15-19.
Luo Naqin,Deng Zhensheng.An extraction algorithm of MRI brain tissue and tumor regions［J］.Beijing Biomedical Engineering，2011，30（1）：15-19.

服務與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频