The Application Research On Linear Transformation Methods For FMRI Data

Brains are the most complex machine in the nature, and for hundreds of years, scientists kept trying to find out the mystery of the brains. With the development of the brain imaging technology, people do more research to the processing analysis of brain function, not only to the anatomical. Function magnetic resonance imaging (fMRI) is a neuron imaging technique which is used to study the human brain's function in response to stimulus from 1990's. The fMRI takes three elements into consideration such as function, image, and anatomy. It is a kind of non-invasive and non-radialized technology and it has high temporal and spatial resolution and can be operated repeatedly as well. Therefore, fMRI has already become an important method today to do researches on brain and lots of methods for brain fMRI data processing came into being and made a lot of results. We discussed the application research on linear transformation method for fMRI data analysis.Current analytical techniques applied to fMRI data require a priori knowledge or specific assumptions about the time courses of processes conteibuting to the measured signals. Since the fMRI signals from the experiments can be regarded as a specific problem of blind source separation, the ICA algorithm can be considered as a method of extracting independent component maps from fMRI signal. Without any priori knowledge about the time courses of processes contributing to the measured signals, ICA is used to separate fMRI data into task-related independent component noisy independent components and other independent component signal. We discussed the theoretical principle and the modeling of fMRI data process by ICA, and design a experiment to analysis the fMRI data by fmrlab.This paper proposes a method of extending theoptimal linear transformation (OLT), an image analysis. technique of feature space, from magnetic resonance imaging (MRI) to functional magnetic resonance imaging (fMRI) so as to improve the activation detection performance over conventional approaches of fMRI analysis. The method was:(1) ideal hemodynamic responses for different stimuli were generated by convolving the theoretical hemodynamic response model with the stimulus timing, (2) considering the ideal hemodynamic responses as hypothetical signature vectors for different activity patterns of interest, OLT was used to extract the features of fMRI data. The resultant feature space had particular geometric clustering properties. It was then classified into different groups, each pertaining to an activity pattern of interest; the applied signature vector for each group was obtained by averaging, (3) using the applied signature vectors, OLT was applied again to generate fMRI composite images with high SNRs for the desired activity patterns. Simulations and a blocked fMRI experiment were employed to validate the proposed method. The simulation and the experiment results indicated the proposed method was capable of improving some conventional methods to be more sensitive to activations, having strong contrast between activations and inactivations, and being more valid for complex activity patterns.