Bayesian characterization of uncertainty in intra-subject non-rigid registration

• Published in: Medical image analysis Vol. 17; no. 5; pp. 538 - 555
• Main Authors: Risholm, Petter, Janoos, Firdaus, Norton, Isaiah, Golby, Alex J., Wells, William M.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.07.2013
• Subjects: Algorithms; Bayes Theorem; Bayesian; Brain - anatomy & histology; Data Interpretation, Statistical; Elastic; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Magnetic Resonance Imaging - methods; MCMC; Non-rigid; Pattern Recognition, Automated - methods; Registration; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Uncertainty; Non-rigid; MCMC; Uncertainty; Elastic; Registration; Bayesian
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2013.03.002

[Display omitted] •Characterize non-parametric posterior distribution on deformations with MCMC.•Marginalize over hyper-parameters.•The registration uncertainty is estimated.•The posterior distribution on deformations can be non-Gaussian and multi-modal. In settings where high-level inferences are made based on registered image data, the registration uncertainty can contain important information. In this article, we propose a Bayesian non-rigid registration framework where conventional dissimilarity and regularization energies can be included in the likelihood and the prior distribution on deformations respectively through the use of Boltzmann’s distribution. The posterior distribution is characterized using Markov Chain Monte Carlo (MCMC) methods with the effect of the Boltzmann temperature hyper-parameters marginalized under broad uninformative hyper-prior distributions. The MCMC chain permits estimation of the most likely deformation as well as the associated uncertainty. On synthetic examples, we demonstrate the ability of the method to identify the maximum a posteriori estimate and the associated posterior uncertainty, and demonstrate that the posterior distribution can be non-Gaussian. Additionally, results from registering clinical data acquired during neurosurgery for resection of brain tumor are provided; we compare the method to single transformation results from a deterministic optimizer and introduce methods that summarize the high-dimensional uncertainty. At the site of resection, the registration uncertainty increases and the marginal distribution on deformations is shown to be multi-modal.