Intensity-based image registration using robust correlation coefficients Export

@article{citeulike:316441, abstract = {The ordinary sample correlation coefficient is a popular similarity measure for aligning images from the same or similar modalities. However, this measure can be sensitive to the presence of "outlier" objects that appear in one image but not the other, such as surgical instruments, the patient table, etc., which can lead to biased registrations. This paper describes an intensity-based image registration technique that uses a robust correlation coefficient as a similarity measure. Relative to the ordinary sample correlation coefficient, the proposed similarity measure reduces the influence of outliers. We also compared the performance of the proposed method with the mutual information-based method. The robust correlation-based method should be useful for image registration in radiotherapy (KeV to MeV X-ray images) and image-guided surgery applications. We have investigated the properties of the proposed method by theoretical analysis, computer simulations, a phantom experiment, and with functional magnetic resonance imaging (MRI) data.}, author = {Kim, Jeongtae and Fessler, J. A.}, citeulike-article-id = {316441}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TMI.2004.835313}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1350900}, doi = {10.1109/TMI.2004.835313}, journal = {Medical Imaging, IEEE Transactions on}, keywords = {coefficients, correlation, robust}, number = {11}, pages = {1430--1444}, posted-at = {2005-09-13 12:24:46}, priority = {2}, title = {Intensity-based image registration using robust correlation coefficients}, url = {http://dx.doi.org/10.1109/TMI.2004.835313}, volume = {23}, year = {2004} }

TY - JOUR ID - citeulike:316441 L3 - citeulike-article-id:316441 N2 - The ordinary sample correlation coefficient is a popular similarity measure for aligning images from the same or similar modalities. However, this measure can be sensitive to the presence of "outlier" objects that appear in one image but not the other, such as surgical instruments, the patient table, etc., which can lead to biased registrations. This paper describes an intensity-based image registration technique that uses a robust correlation coefficient as a similarity measure. Relative to the ordinary sample correlation coefficient, the proposed similarity measure reduces the influence of outliers. We also compared the performance of the proposed method with the mutual information-based method. The robust correlation-based method should be useful for image registration in radiotherapy (KeV to MeV X-ray images) and image-guided surgery applications. We have investigated the properties of the proposed method by theoretical analysis, computer simulations, a phantom experiment, and with functional magnetic resonance imaging (MRI) data. IS - 11 JF - Medical Imaging, IEEE Transactions on EP - 1444 TI - Intensity-based image registration using robust correlation coefficients VL - 23 SP - 1430 KW - coefficients KW - correlation KW - robust AU - Kim, Jeongtae AU - Fessler, JA PY - 2004/// UR - http://dx.doi.org/10.1109/TMI.2004.835313 ER -