Evaluating similarity measures for brain image registration

• Published in: Journal of visual communication and image representation Vol. 24; no. 7; pp. 977 - 987
• Main Authors: Razlighi, Q.R., Kehtarnavaz, N., Yousefi, S.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01-10-2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Brain; Brain image registration; Comparison of similarity measures; Computer science; control theory; systems; Exact sciences and technology; Normalized spatial mutual information; Pattern recognition. Digital image processing. Computational geometry; Similarity measures; Spatial mutual information; Spatial mutual information; Comparison of similarity measures; Normalized spatial mutual information; Similarity measures; Brain image registration; Brain; Image registration; Similarity; Image processing; Image retrieval; Central nervous system; Blurred image; Optimization; Encephalon; Noisy image; Efficiency; Tridimensional image; Metric; Robustness; Mutual information; Normalized Spatial Mutual Information; Similarity Measures; Spatial Mutual Information; Brain Image Registration; Comparison of Similarity Measures
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2013.06.010

•Image registration is the most fundamental problem in neuroimaging.•Functional imaging usefulness is directly depend on the underlying registration.•Many similarity measures (SM) are used in brain image registration.•Comparing the SM are made possible here by a single metric, Robustness.•Shown that robust SM are more reliable in registering degraded and intermodal images.
Evaluation of similarity measures for image registration is a challenging problem due to its complex interaction with the underlying optimization, regularization, image type and modality. We propose a single performance metric, named robustness, as part of a new evaluation method which quantifies the effectiveness of similarity measures for brain image registration while eliminating the effects of the other parts of the registration process. We show empirically that similarity measures with higher robustness are more effective in registering degraded images and are also more successful in performing intermodal image registration. Further, we introduce a new similarity measure, called normalized spatial mutual information, for 3D brain image registration whose robustness is shown to be much higher than the existing ones. Consequently, it tolerates greater image degradation and provides more consistent outcomes for intermodal brain image registration.