Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters
Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters
复制标题
DOI：
10.1016/j.neuroimage.2010.01.005
复制
发表时间：
2010-04-15
期刊：
影响因子：
5.7
通讯作者：
Gaser, Christian
中科院分区：
文献类型：
--
作者：
Franke, Katja;Ziegler, Gabriel;Gaser, Christian
早期识别偏离正常生长和萎缩模式的脑部解剖结构，例如在阿尔茨海默病（AD）中，有可能通过早期干预改善临床结果。最近，达瓦齐科斯等人（2009年）支持了阿尔茨海默病中的病理性萎缩是一个加速衰老过程这一假设，意味着大脑加速萎缩。为了识别更快的大脑萎缩，首先需要一个健康大脑衰老的模型。在此，我们引入一个框架，使用核回归方法从T - 1加权磁共振成像扫描中自动且高效地估计健康受试者的年龄。该方法在650多名年龄在19 - 86岁的健康受试者身上进行了测试，这些受试者的数据来自四台不同的扫描仪。此外，还分析了各种参数对估计准确性的影响。我们的年龄估计框架包括对T - 1加权图像进行自动预处理、通过主成分分析进行降维、训练相关向量机（RVM；蒂平，2000年）用于回归，最后从测试样本中估计受试者的年龄。该框架被证明是一种可靠的、与扫描仪无关的、用于健康受试者年龄估计的高效方法，在测试样本中估计年龄和实际年龄之间的相关系数r = 0.92，平均绝对误差为5年。结果表明相关向量机性能良好，并确定训练样本的数量是预测准确性的关键因素。将该框架应用于轻度阿尔茨海默病患者，得出的平均大脑年龄差距估计（BrainAGE）分数为 + 10年。（C）2010爱思唯尔公司。保留所有权利。
The early identification of brain anatomy deviating from the normal pattern of growth and atrophy, such as in Alzheimer's disease (AD), has the potential to improve clinical outcomes through early intervention. Recently, Davatzikos et al. (2009) supported the hypothesis that pathologic atrophy in AD is an accelerated aging process, implying accelerated brain atrophy. In order to recognize faster brain atrophy, a model of healthy brain aging is needed first. Here, we introduce a framework for automatically and efficiently estimating the age of healthy subjects from their T-1-weighted MRI scans using a kernel method for regression. This method was tested on over 650 healthy subjects, aged 19-86 years, and collected from four different scanners. Furthermore, the influence of various parameters on estimation accuracy was analyzed. Our age estimation framework included automatic preprocessing of the T-1-weighted images, dimension reduction via principal component analysis, training of a relevance vector machine (RVM; Tipping, 2000) for regression, and finally estimating the age of the subjects from the test samples. The framework proved to be a reliable, scanner-independent, and efficient method for age estimation in healthy subjects, yielding a correlation of r = 0.92 between the estimated and the real age in the test samples and a mean absolute error of 5 years. The results indicated favorable performance of the RVM and identified the number of training samples as the critical factor for prediction accuracy. Applying the framework to people with mild AD resulted in a mean brain age gap estimate (BrainAGE) score of + 10 years. (C) 2010 Elsevier Inc. All rights reserved.