基于统计学习的影像遗传学方法综述

近年来随着多模态神经影像技术和基因检测技术的发展，影像遗传学这一交叉学科的研究能够运用脑影像技术将人类大脑的结构与功能作为表型来评价基因对个体的影响，使得人们可以在脑的宏观结构上以更客观的测量手段理解基因对行为或精神疾病的影响.而统计学习方法作为基于数据驱动的关联分析强有力工具，能够充分利用生物标志数据内在的结构信息构建模型来分析易感基因与大脑结构或者功能的相关性，从而更好地揭示脑认知行为或者相关疾病的产生机制.本文首先简要介绍了影像遗传学的研究背景和基本原理，然后回顾了单变量方法在影像遗传学研究中的应用，随后对基于多变量统计学习的基因-影像关联的研究思路和建模方法进行了归纳总结，最后对遗传影像学的未来研究发展方向进行了分析和展望.

A Review of Statistical-learning Imaging Genetics

The past decade has witnessed the increasing development of multimodal neuroimaging and genomic techniques. Imaging genetics, an interdisciplinary field, aims to evaluate and characterize genetic variants in individuals that influence phenotypic measures derived from structural and functional brain images. This strategy is able to reveal the complex mechanisms via macroscopic intermediates from genetic level to cognition and psychiatric disorders in humans. On the other hand, statistical learning methods, as a powerful tool in the data-driven based association study, can make full use of priori-knowledge (inter correlated structure information among imaging and genetic data) for correlation modelling. Therefore, the association study can address the correlations between risk gene and brain structure or function, so as to help explore a better mechanistic understanding of behaviors or disordered brain functions. This paper firstly reviews the related background and fundamental work in imaging genetics and then shows the univariate statistical learning approaches for correlation analysis. Subsequently, it summarizes the main idea and modeling in gene-imaging association studies based on multivariate statistical learning. Finally, this paper presents some prospects of future work.