Wang Yongmei Michelle, Schultz Robert T, Constable R Todd, Staib Lawrence H
Department of Diagnostic Radiology, Yale University School of Medicine, New Haven, CT 06520, USA.
Inf Process Med Imaging. 2003 Jul;18:647-59. doi: 10.1007/978-3-540-45087-0_54.
This paper presents a new and general nonlinear framework for fMRI data analysis based on statistical learning methodology: support vector machines. Unlike most current methods which assume a linear model for simplicity, the estimation and analysis of fMRI signal within the proposed framework is nonlinear, which matches recent findings on the dynamics underlying neural activity and hemodynamic physiology. The approach utilizes spatio-temporal support vector regression (SVR), within which the intrinsic spatio-temporal autocorrelations in fMRI data are reflected. The novel formulation of the problem allows merging model-driven with data-driven methods, and therefore unifies these two currently separate modes of fMRI analysis. In addition, multiresolution signal analysis is achieved and developed. Other advantages of the approach are: avoidance of interpolation after motion estimation, embedded removal of low-frequency noise components, and easy incorporation of multi-run, multi-subject, and multi-task studies into the framework.
本文基于统计学习方法——支持向量机，提出了一种全新的通用非线性框架用于功能磁共振成像（fMRI）数据分析。与目前大多数为简化而假设线性模型的方法不同，在所提出的框架内对fMRI信号的估计和分析是非线性的，这与最近关于神经活动和血液动力学生理基础动态的研究结果相匹配。该方法利用时空支持向量回归（SVR），其中反映了fMRI数据中固有的时空自相关。该问题的新颖表述允许将模型驱动方法与数据驱动方法相结合，从而统一了目前这两种fMRI分析的独立模式。此外，还实现并发展了多分辨率信号分析。该方法的其他优点包括：避免运动估计后的插值、嵌入式去除低频噪声成分，以及易于将多轮、多受试者和多任务研究纳入该框架。
