Nonrigid Image Registration of Brain MR Images Using Normalized Mutual Information

Registration is an advanced technique which maps two images spatially and can produce an informative image. Intensity-based similarity measures are increasingly used for medical image registration that helps clinicians for faster and more effective diagnosis. Recently, mutual information (MI)-based image registration techniques have become popular for multimodal brain images. In this chapter, normalized mutual information (NMI) method has been employed for brain MR image registration. Here, the intensity patterns are encoded through similarity measure technique. NMI 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 B-spline method. NMI-based image registration is performed for similarity measure between the reference and floating image. Optimal evaluation of joint probability distribution of the two images is performed using parzen window interpolation method. The hierarchical approach to nonrigid registration based on NMI is presented in which the images are locally registered and nonrigidly interpolated. The proposed method for nonrigid registration is validated with both clinical and artificial brain MR images. The obtained results show that the images could be successfully registered with 95 % of correctness.

[1]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[2]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[3]  Josien P. W. Pluim,et al.  Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines , 2007, IEEE Transactions on Image Processing.

[4]  Pramod K. Varshney,et al.  Mutual information-based CT-MR brain image registration using generalized partial volume joint histogram estimation , 2003, IEEE Transactions on Medical Imaging.

[5]  Max A. Viergever,et al.  Interpolation Artefacts in Mutual Information-Based Image Registration , 2000, Comput. Vis. Image Underst..

[6]  Bostjan Likar,et al.  A hierarchical approach to elastic registration based on mutual information , 2001, Image Vis. Comput..

[7]  Philippe C. Cattin,et al.  Non-rigid registration of multi-modal images using both mutual information and cross-correlation , 2008, Medical Image Anal..

[8]  Max A. Viergever,et al.  Image registration by maximization of combined mutual information and gradient information , 2000, IEEE Transactions on Medical Imaging.

[9]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[10]  Colin Studholme,et al.  Deformation-based mapping of volume change from serial brain MRI in the presence of local tissue contrast change , 2006, IEEE Transactions on Medical Imaging.

[11]  Daniel Rueckert,et al.  Diffeomorphic Registration Using B-Splines , 2006, MICCAI.

[12]  A. Ben Hamza,et al.  An Entropy-Based Technique for Nonrigid Medical Image Alignment , 2011, IWCIA.

[13]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1995, Proceedings of IEEE International Conference on Computer Vision.