A contextual maximum likelihood framework for modeling image registration

Wachinger, Christian; Navab, Nassir

doi:10.1109/cvpr.2012.6247902

Cited by 3 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we leverage techniques for robust estimation that require comparable intensity values, as in the monomodal registration setup. For this purpose, we use a probabilistic framework [Wachinger and Navab, 2012b] that introduced layers of latent random variables, called description layers. Figure 1 In our study, we use the description layers to store a structural representation of images.…”

Section: Probabilistic Model For Rrmentioning

confidence: 99%

“…Commonly used description layers result from image filtering, image gradients, or dense feature descriptors. As we are interested in a modality‐invariant description, we use a structural representation with entropy images, justified by applying the asymptotic equipartition property on the coupling terms [Wachinger and Navab, ]. Under the assumption that the information content across modalities is similar, entropy images reduce the multimodal setup to a monomodal registration problem.…”

Section: Robust Multimodal Registrationmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐modal robust inverse‐consistent linear registration

Wachinger

Golland

Magnain

et al. 2014

Human Brain Mapping

View full text Add to dashboard Cite

Registration performance can significantly deteriorate when image regions do not comply with model assumptions. Robust estimation improves registration accuracy by reducing or ignoring the contribution of voxels with large intensity differences, but existing approaches are limited to monomodal registration. In this work, we propose a robust and inverse-consistent technique for crossmodal, affine image registration. The algorithm is derived from a contextual framework of image registration. The key idea is to use a modality invariant representation of images based on local entropy estimation, and to incorporate a heteroskedastic noise model. This noise model allows us to draw the analogy to iteratively reweighted least squares estimation and to leverage existing weighting functions to account for differences in local information content in multimodal registration. Furthermore, we use the nonparametric windows density estimator to reliably calculate entropy of small image patches. Finally, we derive the Gauss–Newton update and show that it is equivalent to the efficient secondorder minimization for the fully symmetric registration approach. We illustrate excellent performance of the proposed methods on datasets containing outliers for alignment of brain tumor, full head, and histology images.

show abstract

Section: Probabilistic Model For Rrmentioning

confidence: 99%

Section: Robust Multimodal Registrationmentioning

confidence: 99%

Multi‐modal robust inverse‐consistent linear registration

Wachinger

Golland

Magnain

et al. 2014

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…Assuming a Gaussian distribution of the density p, i.i.d. coordinate samples, and various intensity mappings between the images, popular similarity measures such as sum of squared differences (SSD), normalized cross correlation (NCC), correlation ratio (CR), and mutual information (MI) can be derived from the log-likelihood term log p(I j |I i ) [26]- [28]. APE therefore presents a framework for similarity measures.…”

Section: Accumulated Pair-wise Estimatesmentioning

confidence: 99%

Simultaneous Registration of Multiple Images: Similarity Metrics and Efficient Optimization

Wachinger

Navab

2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

We address the alignment of a group of images with simultaneous registration. Therefore, we provide further insights into a recently introduced framework for multivariate similarity measures, referred to as accumulated pair-wise estimates (APE), and derive efficient optimization methods for it. More specifically, we show a strict mathematical deduction of APE from a maximum-likelihood framework and establish a connection to the congealing framework. This is only possible after an extension of the congealing framework with neighborhood information. Moreover, we address the increased computational complexity of simultaneous registration by deriving efficient gradient-based optimization strategies for APE: Gauss-Newton and the efficient second-order minimization (ESM). We present next to SSD the usage of intrinsically nonsquared similarity measures in this least squares optimization framework. The fundamental assumption of ESM, the approximation of the perfectly aligned moving image through the fixed image, limits its application to monomodal registration. We therefore incorporate recently proposed structural representations of images which allow us to perform multimodal registration with ESM. Finally, we evaluate the performance of the optimization strategies with respect to the similarity measures, leading to very good results for ESM. The extension to multimodal registration is in this context very interesting because it offers further possibilities for evaluations, due to publicly available datasets with ground-truth alignment.

show abstract

Nonrigid Registration of Ultrasound and MRI Using Contextual Conditioned Mutual Information

Rivaz

Karimaghaloo

Fonov

et al. 2014

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Mutual information (MI) quantifies the information that is shared between two random variables and has been widely used as a similarity metric for multi-modal and uni-modal image registration. A drawback of MI is that it only takes into account the intensity values of corresponding pixels and not of neighborhoods. Therefore, it treats images as "bag of words" and the contextual information is lost. In this work, we present Contextual Conditioned Mutual Information (CoCoMI), which conditions MI estimation on similar structures. Our rationale is that it is more likely for similar structures to undergo similar intensity transformations. The contextual analysis is performed on one of the images offline. Therefore, CoCoMI does not significantly change the registration time. We use CoCoMI as the similarity measure in a regularized cost function with a B-spline deformation field and efficiently optimize the cost function using a stochastic gradient descent method. We show that compared to the state of the art local MI based similarity metrics, CoCoMI does not distort images to enforce erroneous identical intensity transformations for different image structures. We further present the results on nonrigid registration of ultrasound (US) and magnetic resonance (MR) patient data from image-guided neurosurgery trials performed in our institute and publicly available in the BITE dataset. We show that CoCoMI performs significantly better than the state of the art similarity metrics in US to MR registration. It reduces the average mTRE over 13 patients from 4.12 mm to 2.35 mm, and the maximum mTRE from 9.38 mm to 3.22 mm.

show abstract

A contextual maximum likelihood framework for modeling image registration

Cited by 3 publications

References 39 publications

Multi‐modal robust inverse‐consistent linear registration

Multi‐modal robust inverse‐consistent linear registration

Simultaneous Registration of Multiple Images: Similarity Metrics and Efficient Optimization

Nonrigid Registration of Ultrasound and MRI Using Contextual Conditioned Mutual Information

Contact Info

Product

Resources

About