Incorporating a measure of local scale in voxel-based 3-D image registration

• Published in: IEEE transactions on medical imaging Vol. 22; no. 2; pp. 228 - 237
• Main Authors: Nyul, L.G., Udupa, J.K., Saha, P.K.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.02.2003; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Algorithms; Biological and medical sciences; Brain - anatomy & histology; Correlation; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image registration; Image segmentation; Imaging, Three-Dimensional - methods; Information filtering; Information filters; Magnetic heads; Magnetic resonance imaging; Male; Medical sciences; Middle Aged; Multiple sclerosis; Multiple Sclerosis - diagnosis; Mutual information; Protocols; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Statistics as Topic; Subtraction Technique
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2002.808358

We present a new class of approaches for rigid-body registration and their evaluation in studying multiple sclerosis (MS) via multiprotocol magnetic resonance imaging (MRI). Three pairs of rigid-body registration algorithms were implemented, using cross-correlation and mutual information (MI), operating on original gray-level images, and utilizing the intermediate images resulting from our new scale-based method. In the scale image, every voxel has the local "scale" value assigned to it, defined as the radius of the largest ball centered at the voxel with homogeneous intensities. Three-dimensional image data of the head were acquired from ten MS patients for each of six MRI protocols. Images in some of the protocols were acquired in registration. The registered pairs were used as ground truth. Accuracy and consistency of the six registration methods were measured within and between protocols for known amounts of misregistrations. Our analysis indicates that there is no "best" method. For medium misregistration, the method using MI, for small and large misregistration the method using normalized cross-correlation performs best. For high-resolution data the correlation method and for low-resolution data the MI method, both using the original gray-level images, are the most consistent. We have previously demonstrated the use of local scale information in fuzzy connectedness segmentation and image filtering. Scale may also have potential for image registration as suggested by this work.