School of Cancer and Enabling Sciences, University of Manchester/MAHSC, Wolfson Molecular Imaging Centre, Manchester, England, UK.
Neuroimage. 2011 Jun 1;56(3):1382-5. doi: 10.1016/j.neuroimage.2011.02.036. Epub 2011 Feb 19.
The assessment of accuracy and robustness of multivariate analysis of FDG-PET brain images as presented in [Markiewicz, P.J., Matthews, J.C., Declerck, J., Herholz, K., 2009. Robustness of multivariate image analysis assessed by resampling techniques and applied to FDG-PET scans of patients with Alzheimer's disease. Neuroimage 46, 472-485.] using a homogeneous sample (from one centre) of small size is here verified using a heterogeneous sample (from multiple centres) of much larger size. Originally the analysis, which included principal component analysis (PCA) and Fisher discriminant analysis (FDA), was established using a sample of 42 subjects (19 Normal Controls (NCs) and 23 Alzheimer's disease (AD) patients) and here the analysis is verified using an independent sample of 166 subjects (86 NCs and 80 ADs) obtained from the ADNI database. It is shown that bootstrap resampling combined with the metric of the largest principal angle between PCA subspaces as well as the deliberate clinical misdiagnosis simulation can predict robustness of the multivariate analysis when used with new datasets. Cross-validation (CV) and the .632 bootstrap overestimated the predictive accuracy encouraging less robust solutions. Also, it is shown that the type of PET scanner and image reconstruction method has an impact on such analysis and affects the accuracy of the verification sample.
评估[Markiewicz, P.J., Matthews, J.C., Declerck, J., Herholz, K., 2009. Robustness of multivariate image analysis assessed by resampling techniques and applied to FDG-PET scans of patients with Alzheimer's disease. Neuroimage 46, 472-485.]中基于 FDG-PET 脑图像的多元分析的准确性和稳健性，使用的是同质样本（来自一个中心）的小尺寸，这里使用的是异质样本（来自多个中心）的大尺寸来验证。最初的分析包括主成分分析（PCA）和 Fisher 判别分析（FDA），是使用 42 个样本（19 个正常对照组（NCs）和 23 个阿尔茨海默病（AD）患者）建立的，这里使用来自 ADNI 数据库的 166 个样本（86 个 NCs 和 80 个 ADs）进行了验证。结果表明，使用 bootstrap 重采样结合 PCA 子空间之间最大主角度的度量以及故意的临床误诊模拟可以预测多元分析的稳健性，用于新数据集。交叉验证（CV）和.632 bootstrap 高估了预测准确性，鼓励使用不太稳健的解决方案。此外，还表明 PET 扫描仪的类型和图像重建方法对这种分析有影响，并影响验证样本的准确性。
