Simultaneous segmentation and registration for functional MR images

A simultaneous segmentation and registration model is proposed for functional MR (fMR) image alignment that is significant for minimizing motion artifacts on fMRI data analysis. Due to T-2* weighted signal loss and deceased resolution, in fMR images, the images can't be aligned reliably by only using image information. Our approach uses the shape of a contour pre-segmented in a high resolution image to and find the unknown contour in each of the time series images, and the spatial transform that maps the interface to the given contour. This is achieved by minimizing an energy functional depending on the information of the image gradient and the shape of interest so that the boundary of the object can be captured either by higher gradient or by the prior knowledge of its shape. In the meantime, the registration is achieved by the transformation determined in shape matching. The model has been tested both on synthetic data and fMR brain image data. The experimental results showed the effectiveness of this model in feature determination and time series image registration. The existence of the solution to the proposed model is also discussed.