Department of Signal Theory, Networking and Communications, ETSIIT 18071, University of Granada, Granada, Spain.
Med Phys. 2010 Nov;37(11):6084-95. doi: 10.1118/1.3488894.
This article presents a computer-aided diagnosis technique for improving the accuracy of the early diagnosis of Alzheimer's disease (AD). Two hundred and ten 18F-FDG PET images from the ADNI initiative [52 normal controls (NC), 114 mild cognitive impairment (MCI), and 53 AD subjects] are studied.
The proposed methodology is based on the selection of voxels of interest using the t-test and a posterior reduction of the feature dimension using factor analysis. Factor loadings are used as features for three different classifiers: Two multivariate Gaussian mixture model, with linear and quadratic discriminant function, and a support vector machine with linear kernel.
An accuracy rate up to 95% when NC and AD are considered and an accuracy rate up to 88% and 86% for NC-MCI and NC-MCI,AD, respectively, are obtained using SVM with linear kernel.
Results are compared to the voxel-as-features and a PCA- based approach and the proposed methodology achieves better classification performance.
本文提出了一种计算机辅助诊断技术，以提高阿尔茨海默病（AD）早期诊断的准确性。本研究使用了 ADNI 倡议的 210 个 18F-FDG PET 图像[52 名正常对照（NC），114 名轻度认知障碍（MCI）和 53 名 AD 患者]。
该方法基于使用 t 检验选择感兴趣的体素，以及使用因子分析对特征维度进行后向缩减。因子负荷用作三种不同分类器的特征：两个多元高斯混合模型，具有线性和二次判别函数，以及具有线性核的支持向量机。
使用线性核支持向量机，当考虑 NC 和 AD 时，准确率高达 95%，对于 NC-MCI 和 NC-MCI-AD，准确率分别高达 88%和 86%。
将结果与体素特征和基于 PCA 的方法进行比较，该方法实现了更好的分类性能。
