北京生物医学工程

双向抑郁症患者脑磁共振图像纹理特征

Changes of texture features of brain magnetic resonanceimages in bipolar depression patients

作者：周震王洪刘春红

单位：首都医科大学生物医学工程学院(北京100069)

分类号：R318.04

出版年·卷·期（页码）：2017·36·6（597-600）

摘要：

目的研究双向抑郁症患者与健康人群脑部磁共振图像在前额叶脑白质区的纹理差异。方法在抑郁症患者组和健康对照组中随机各选取8名志愿者，进行相同的脑部磁共振扫描，选取左右额叶脑白质作为研究对象，提取实验组和对照组样本的纹理特征，使用最小分类误差与最小平均相关系数法对纹理特征进行筛选及分类比较研究。结果通过比较原始数据分析(raw data analysis，RDA)、主成分分析(principal component analysis，PCA)、线性判别分析(linear discriminant analysis，LDA)、非线性判别分析(nonlinear discriminant analysis，NDA)4种分类方法，发现LDA和NDA方法对样本纹理分类正确率高于RDA和PCA分类方法。结论抑郁症患者与健康人群脑部磁共振图像的前额叶脑白质区纹理特征存在差异。

Objective To investigate the texture feature differences in prefrontal white matter between bipolar depression patients and normal people.Methods Eight volunteers were randomly selected from the bipolar depression patients and the normal control group respectively，and underwent the same MRI scans of the brain.The left and right prefrontal white matters were selected as research objects in the same brain area of MRI.The texture features of the experimental and control samples were extracted based on the minimized POE + ACC methods.Results The classification accuracy of RDA and LDA were higher than that of PCA and NDA.Conclusions The texture features of prefrontal white matters are different between the control group and depression patient group.

参考文献：

［1］Fitzgerald PJ.Gray colored glasses:is major depression partially a sensory perceptual disorder［J］.Journal of Affective Disorders，2013,151(2):418-422.

［2］Lang UE，Borgwardt S.Molecular mechanisms of depression:perspectives on new treatment strategies［J］.Cell Physiology &Biochemistry International Journal of Experimental Cellular Physiology Biochemistry & Pharmacology，2013，31( 6):761-777.

［3］Hasler G，Northoff G.Discovering imaging endophenotypes for major depression［J］.Molecular Psychiatry，2011，16(6):604-619.

［4］马春燕，张晨.抑郁症神经类症机制研究进展［J］.中国医药导报，2017，14(14)：33-35.

Ma CY,Zhang C. Progress of neuroinflammation mechanism in depression［J］. China Medical Harald,2017,14(14):33-35.

［5］谭金凤,伍珊珊,徐雷,等.前额叶皮层与双任务加工执行功能［J］.心理科学进展，2013，21(12):2127-2135.

Tan JF，Wu SS，Xu L，et al.Prefrontal cortex with executive functions involved in dual-task performance［J］.Advances in Psychological Science，2013，21(12):2127-2135.

［6］Haralick R.Statistical and structural approaches to texture［J］.Proceedings of the IEEE，2005，67( 5):786-804.

［7］Mao J，Jain AK.Artificial neural networks for feature extraction and multivariate data projection［J］.IEEE Transactions on Neural Networks,1995,6(2):296-317.

［8］Kwak N，Choi CH.Input Feature selection by mutual information based on Parzen window［J］.IEEE Transactions on Patter Analysis and Machine Inteligence，2002，24(12):1667-1671.

［9］Lerski RA，Straughan K，Schad LR，et al.MR image texture analysis-an approach to tissue characterization［J］.Magnetic Resonance Imaging，1993，11(6):873-887.

［10］Swets DL，Weng J.Using discriminant eigenfeatures for image retrieval［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，1996,18( 8):831-836.

［11］Materka A，Strzelecki M，Lerski R，et al.Feature evaluation of texture test objects for magnetic resonance imaging［M］// Pietikainen MK.Texture analysis in machine vision.New Jersey:World Scientific Publishing Company，2000:197-206.

［12］Tourassi GD，Frederick ED，Markey MK，et al.Application of the mutual information criterion for feature selection in computer-aided diagnosis［J］.Medical Physics，2001,28(12):2394-2402.

［13］Hu Y，Dennis TJ.Textured image segmentation by context enhanced clustering［J］.IEE Proceedings-Vision，Image and Signal Processing，1994，141( 6):413-421.

［14］Gallinari P，Thiria S，Badran F，et al.On the relations between discriminant analysis and multilayer perceptrons［J］.Neural Networks,1991，4(3):349-360.

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