Book Chapter Published

Abstract

How to effectively conduct functional magnetic resonance imaging (fMRI) data analysis is very important for the promotion and application of fMRI technology. Compared with the traditional fMRI data analysis methods, the strategy has unique advantages in fMRI data analysis by incorporating prior knowledge into the algorithm process. In this chapter, the introduction of prior knowledge into independent component analysis is given as an example to illustrate the advantages of prior knowledge in many aspects, such as reducing the computational complexity and improving the analysis accuracy. Then, this chapter summarizes the main results of such methods in existing research and further discusses the ways of introducing different types of prior knowledge into the model and the limitations of existing methods. Finally, this chapter explains how to mine deeper prior knowledge from the data itself, and how to introduce prior knowledge into other fMRI data analysis methods in the future.