P-SPLINE BASED NONRIGID BRAIN MR IMAGE REGISTRATION USING REGIONAL MUTUAL INFORMATION

Registration is an advanced technique which maps two images spatially and produces an informative image. Intensity based similarity measures are increasingly used for medical image registration, which helps clinicians for faster and more effective diagnosis. Recently mutual information based image registration techniques are popular for both monomodal and multimodal brain images. In this paper, regional mutual information method has been employed by incorporating P-spline interpolation method for deformed nonrigid brain MR image registration. Here some regional information are encoded through similarity measure technique. Regional mutual information is an entropy based measure that is invariant to the overlapped regions of the two images. To take care of the deformations, transformation of the floating image is performed using Penalized spline method. Regional mutual information based image registration is performed for similarity measure between the reference and floating image. The hierarchical approach to nonrigid registration based on regional mutual information is presented in which the images are locally registered and nonrigidly interpolated. The proposed method for nonrigid registration is validated with clinical brain MR images. The obtained results show that the images could be successfully registered with less misregistration error.