阿尔茨海默病患者脑MR图像二维及三维纹理分析比较研究  被引量:6

2D and 3D Texture Features of Corpus Caliosum in Patients with Alzheimer Disease Based on MR Images

在线阅读下载全文

作  者:夏翃[1] 刘卫芳[1] 王旭[1] 童隆正[1] 

机构地区:[1]首都医科大学生物医学工程学院,北京100069

出  处:《北华大学学报(自然科学版)》2013年第5期553-556,共4页Journal of Beihua University(Natural Science)

基  金:国家自然科学基金项目(81071128);北京市教育委员会科技发展计划项目(SQKM201210025009);首都医科大学基础临床科研项目(11JL29);首都医科大学横向课题项目(736001)

摘  要:目的研究阿尔茨海默病(Alzheimer Disease,AD)患者脑MR图像的二维、三维纹理特征,比较二维、三维纹理分析在AD临床辅助诊断中的作用,以期为AD早期诊断提供更好的帮助.方法选取15例AD患者(AD组)及15例健康对照者(NC组)的MR图像进行二维、三维纹理分析,采用灰度共生矩阵提取每位受试者胼胝体的二维、三维纹理特征,包括能量、对比度、相关、逆差矩和熵等,比较两组样本二维、三维纹理特征及各纹理特征间是否存在显著性差异.结果提取的5个三维纹理参数中只有1个(相关)两组间没有统计学意义(P>0.05),其余4个两组间均存在显著统计学意义(P<0.05);同样的5个二维纹理参数中有3个(能量、相关、熵)两组间没有统计学意义(P>0.05).结论与二维纹理特征相比,三维纹理提供了更全面的信息,可能更有助于临床辅助诊断.Objective The aim of this study is to compare 2D texture analysis and 3D texture analysis in the clinical diagnosis of AD to explore 2D and 3D texture features of corpus callosum in magnetic resonance images from the patients with alzheimer disease (AD). Method 2D and 3D texture analysis was performed on 15 AD patients and 15 normal controls (NC). The texture features ( energy, contrast, correlation, homogeneity and entropy) were extracted from gray level co-occurrence matrix. The significant differences between two groups were tested. Results The results showed that 3D texture features (energy, contrast, homogeneity and entropy) had significant differences ( P 〈 0. 05 ) between AD and NC. Meanwhile, 2D texture features ( contrast and homogeneity) also had significant differences (P 〈 0.05 ) between AD and NC. Conclusion Compared to 2D texture analysis,3D texture features of the microcosmic pathological changes in corpus caliosum of AD patients can reflect more information,and may be more helpful to the early diagnosis of AD.

关 键 词:阿尔茨海默病 MRI 纹理分析 胼胝体 

分 类 号:R749.1[医药卫生—神经病学与精神病学] R445.2[医药卫生—临床医学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象