Iterative Non-Rigid Image Registration in Brain MRI Images

Abstract

Non-rigid image registration plays a significant role in the medical imaging domain. It involves deformations of moving image pixels according to fixed or reference image anatomy. Accurate image registration is required for accurate medical diagnosis and clinical applications. Non-rigid image registration uses optimization techniques to find the best possible solution. The solution obtained using a single run of non-rigid image registration may be optimal but not much accurate. In order to increase accuracy in non-rigid image registration, multiple runs are required to improve the performance. Here in our research methodology, we used the Demon algorithm as non-rigid image registration for brain MRI images of patients with tumors. There is significant improvement i.e., an average of 66.61% decrease in the error of the results of iterative Demon algorithm as compared to non-iterative Demon algorithm.