北京生物医学工程

阿尔茨海默病的MR图像三维纹理的灰度游程分析

Gray level run length matrices analysis of MR images in Alzheimer’s disease

作者：夏翃刘卫芳童隆正王旭周震

单位：首都医科大学生物医学工程学院(北京100069)

关键词：阿尔茨海默病; MRI; 胼胝体; 灰度游程长矩阵

分类号：

出版年·卷·期（页码）：2013·32·6（575-578）

摘要：

目的灰度游程长矩阵参数可以反映图像纹理的粗细及均匀程度。本研究采用该方法研究阿尔茨海默病

(Alzheimer’s disease, AD)患者脑MR图像中胼胝体的三维纹理特征，以反映AD患者胼胝体部位的病理变化

，从而探索该纹理特征分析方法在该疾病诊断中的应用。方法选取18例AD患者及18例健康对照者，采用灰

度游程长矩阵提取每位受试者胼胝体部位的4个三维纹理特征参数：短游程因子、长游程因子、灰度不均匀

度和游程长不均匀度。比较两组间各纹理特征的差异，并分析这些纹理参数与临床广泛应用的简易智能状态

检查量表(mini-mental state examination, MMSE)评分之间的相关性。结果 4个纹理参数两组相比较均有

显著性差异，且与MMSE评分均具有相关性。结论基于三维纹理特征的灰度游程分析法能在一定程度上反映

出AD患者胼胝体部位的病理变化，可能用于该疾病的临床诊断。

Objective To explore the 3D texture features of corpus callosum in magnetic

resonance images from the patients with Alzheimer’s disease and to discuss the application of

texture features in diagnosis of AD. Methods T1-weighted MRIs of 18 AD patients and 18 normal

controls were selected. 3D texture features of the corpus callosum, including short run

emphasis, long run emphasis, grey level nonuniformity and run length nonuniformity, were

extracted from the run length matrix. Finally, statistic significance was tested between the

two groups, and the correlations between the parameters and the widely used method—mini-

mental state examination (MMSE) were calculated. Results The differences of the 3D texture

features were significant between the two groups, and they were correlated with MMSE scores.

Conclusions 3D texture analysis can reflect the pathological changes of corpus callosum in

patients with AD and may be helpful to the diagnosis.

参考文献：

［1］Alzheimer’s Disease International. World Alzheimer Report ［R］. Alzheimer’s Disease

International, 2012.
［2］Zhang Zhenxin, Zahne GEP, Román GC, et al. Dementia subtypes in China: prevalence in

Beijing，Xian，Shanghai，and Chengdu ［J］. Archives of Neurology, 2005, 62:447-53.
［3］中华医学会精神分会. CCMD-3中国精神障碍分类与诊断标准第3版［M］. 济南：山东科学技术出版社,

2001: 87-89.
Chinese Society of Psychiatry. CCMD-3 Chinese classification and diagnostic criteria of mental

disorders. Jinan : Shandong Science & Technology Press, 2001: 87-89.
［4］de Oliveira MS, Balthazar MLF, D’Abreu A, et al. MR imaging texture analysis of the

corpus callosum and thalamus in amnestic mild cognitive impairment and mild Alzheimer disease

［J］. AJNR, 2011, 32: 60-66.

［5］Castellano G, Bonilha L, Li LM, et al. Texture analysis of medical images［J］. Clinical

Radiology, 2004,59(12): 1061-1069.
［6］Georgiadis JP，Cavouras D，Kalatzis I，et al. Enhancing the discrimination accuracy

between metastases, gliomas and meningiomas on brain MRI by volumetric textural feamres and

ensemble pattem recognition methods［J］. Magnetic Resonance Imaging, 2009, 27: 120-130.
［7］ El-Baz A, Casanova MF, Gimel’farb G, et a1. Autism diagnostics by 3D texture analysis

of cerebral white matter gyrification［C］ . International Conference on Medical Image

Computing and Computer—Assisted Intervention(MICCAI 2007), 2007，10( 2): 882-890.
［8］Mahmoud-Ghoneima D, Toussaintb G, Constans JM, et al. Three dimensional texture analysis

in MRI: a preliminary evaluation in gliomas［J］. Magnetic Resonance Imaging, 2003, 21: 983-

987.
［9］刘卫芳，夏翃，周震，等．多发性硬化患者脑磁共振图像的纹理分析［J］. 中国医学影像学杂志,

2013, 21(4): 297-300.
Liu Weifang, Xia Hong, Zhou Zhen, et al. Texture analysis on magnetic resonance imaging in

patients with multiple sclerosis［J］. Chinese Journal of Medical Imaging, 2013, 21(4): 297-

300.
［10］Galloway M M. Texture analysis using gray level run lengths. Comput［J］. Graphics

Image Process,1975, 4: 172-179.
［11］Wagner F, Gryanik A, Schulz-Wendtland, et al. 3D Characterization of texture:

evaluation for the potential application in mammographic mass diagnosis［J］. Biomed Tech,

2012, 57: 490-493.
［12］Arunadevi B,Deepa SN. Texture analysis for 3D classification of brain tumor tissues［J］

. Przeglad Elektrotechniczny, ISSN 0033-2097, R. 89 NR 4/2013.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录