A Hybrid Registration Method for Brain Image Analysis

In this study, a robust registration scheme is proposed to overcome the inconsistent-volume problem associated with clinical image data for neural degeneration assessment. This scheme is a hybrid process including coarse registration using principal axes alignment and then fine-tuning the registration using a combination of maximal cross-section area detection and the general Hough transform. The CT images from SPECT CT scans were used as the medium to register the MR and SPECT images, such that the brain structure delineated in the MR image can be mapped onto the SPECT image in the corresponding area. The results from two clinical datasets all show improved accuracy of registration as compared with the results obtained using conventional principal axes alignment alone.