轻度认知障碍转化阿尔兹海默病影像预测研究

发布时间：2018-05-24 18:13

本文选题：轻度认知障碍 + 阿尔兹海默病　；参考：《安徽大学学报(自然科学版)》2014年02期

【摘要】：基于结构核磁共振影像,探讨轻度认知障碍向阿尔兹海默病转化情况.选取152例轻度认知障碍、101例阿尔兹海默病、97例正常对照组的结构核磁共振影像为研究对象.首先,采取独立成分分析方法对阿尔兹海默病和正常对照样本进行组间特征提取;其次,执行感兴趣体素分析,获取组间差异特征信息,并将轻度认知障碍样本在阿尔兹海默病和正常对照组的特征空间上进行表达,获取轻度认知障碍样本特征信息;最后,运支持向量机,对轻度认知障碍样本进行转化预测.测试结果:预测准确率、灵敏度、特异度分别达到80.26%、86.30%、74.68%.结果显示,利用阿尔兹海默病和正常对照个体之间的差异特征能够比较准确地对轻度认知障碍向阿尔兹海默病转化进行预测.
[Abstract]:To investigate the transformation of mild cognitive impairment to Alzheimer's disease based on structural magnetic resonance imaging. A total of 152 patients with mild cognitive impairment (MCI) and 101 patients with Alzheimer's disease (AD) were studied on structural MRI images of 97 normal controls. Firstly, independent component analysis (ICA) was used to extract the characteristics of Alzheimer's disease (AD) and normal controls. Secondly, VIEA was performed to obtain the information of differences between groups. The samples of mild cognitive impairment were expressed in the feature space of Alzheimer's disease and normal control group to obtain the feature information of mild cognitive impairment samples. Finally, support vector machine was used to predict the transformation of mild cognitive impairment samples. The test results showed that the accuracy, sensitivity and specificity of prediction were 80.26% and 86.30% and 74.68%, respectively. The results showed that the differential characteristics between Alzheimer's disease and normal individuals could accurately predict the transition of mild cognitive impairment to Alzheimer's disease.
【作者单位】：上海海事大学信息工程学院;
【基金】：上海市教育委员会科研创新资助项目(12YZ116)
【分类号】：R749.16

【共引文献】