Liver Motion Estimation via Locally Adaptive Over-Segmentation Regularization

Papież, Bartłomiej W.; Franklin, Joseph B.; Heinrich, Mattias P.; Gleeson, Fergus; Schnabel, Julia A.

doi:10.1007/978-3-319-24574-4_51

Cited by 15 publications

(31 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, we developed a method to automatically segment the diseased bowel wall from post-contrast MR images [33]. An obvious way to enhance the registration might be to give high priority to such regions [34]. However, we have found that this does not lead to a significant improvement, which we attribute to the small size of the regions.…”

Section: Discussionmentioning

confidence: 92%

A hybrid optimization strategy for registering images with large local deformations and intensity variations

Vliet

Stoker

et al. 2017

Int J CARS

View full text Add to dashboard Cite

Purpose To develop a method for intra-patient registration of pre-and post-contrast abdominal MR images with large local deformations and large intensity variations. Method A hybrid method is proposed to deal with this problem. It consists of two coupled techniques: (1) descriptor matching (DM) at the original resolution using a discrete optimization strategy to avoid getting trapped in a local minimum; (2) continuous optimization to refine the registration outcome based on autocorrelation of local image structure (ALOST). Our method-called DM-ALOST-has become insensitive to the local uptake of contrast agent by exploiting the mean phase and the phase congruency extracted from the multi-scale monogenic signal. The method was extensively tested on abdominal MR data of 30 patients with Crohn's disease. Results DM-ALOST produced significantly larger mean Dice coefficients than two state-of-the-art methods ( p < 0.05). Conclusion Both qualitative and quantitative tests demonstrated improved registration using the proposed method compared to the state-of-the-art. The DM-ALOST method facilitates measurement of corresponding features from different abdominal MR images, which can aid to assess certain diseases, particularly Crohn's disease.

show abstract

Section: Discussionmentioning

confidence: 92%

A hybrid optimization strategy for registering images with large local deformations and intensity variations

Vliet

Stoker

et al. 2017

Int J CARS

View full text Add to dashboard Cite

show abstract

“…Registered non-contrast-enhanced time series are manually segmented and contrast enhancements within the different tissue classes are simulated based on pharmacokinetic modeling to generate a pseudo-ground truth. A DIR that is suitable for aligning both common clinical hepatic DCE-MRI as well as longer time series was proposed by Papiez et al [ 12 ]. The method was evaluated based on manually annotated landmarks and an analysis of the deformation fields.…”

Section: Introductionmentioning

confidence: 99%

Landmark-based evaluation of a deformable motion correction for DCE-MRI of the liver

et al. 2018

View full text Add to dashboard Cite

Purpose Annotation of meaningful landmark ground truth on DCE-MRI is difficult and laborious. Motion correction methods applied to DCE-MRI of the liver are thus mostly evaluated using qualitative or indirect measures. We propose a novel landmark annotation scheme that facilitates the generation of landmark ground truth on larger clinical datasets. Methods In our annotation scheme, landmarks are equally distributed over all time points of all available dataset cases and annotated by multiple observers on a per-pair basis. The scheme is used to annotate 26 DCE-MRI of the liver. A subset of the ground truth is used to optimize parameters of a deformable motion correction. Several variants of the motion correction are evaluated on the remaining cases with respect to distances of corresponding landmarks after registration, deformation field properties, and qualitative measures. Results A landmark ground truth on 26 cases could be generated in under 12 h per observer with a mean inter-observer distance below the mean voxel diagonal. Furthermore, the landmarks are spatially well distributed within the liver. Parameter optimization significantly improves the performance of the motion correction, and landmark distance after registration is 2 mm. Qualitative evaluation of the motion correction reflects the quantitative results. Conclusions The annotation scheme makes a landmark-based evaluation of motion corrections for hepatic DCE-MRI practically feasible for larger clinical datasets. The comparably large number of cases enables both optimization and evaluation of motion correction methods.

show abstract

“…that the deformation field be a diffeomorphism [3]. Alternatively, in order to accurately model local deformations, a number of local structure or motion preservation models have been proposed [4][5][6]. However, the deformations within or between human organs are often highly complex and do not occur at a single spatial scale.…”

Section: Introductionmentioning

confidence: 99%

“…Such structures and connections between them can be represented for example by a MST, which has been shown to replicate well the underlying tissue properties and structure of anatomical connectivity [8]. In contrast to recently proposed anisotropic filter [4], bilateral filter [5], and guided image filter [6] models, the proposed new regularization model implicitly extends local filter kernels to their non-local counterparts by simultaneous consideration of spatial and intensity proximity together with the connectivity of voxel-based nodes. The new MST-based model replaces the Gaussian smoothing originally incorporated in Thirion's Demons [2,3] via employing an efficient MST non-local cost aggregation algorithm [9] to perform regularization on the estimated displacement field.…”

Section: Introductionmentioning

confidence: 99%

Non-local Graph-Based Regularization for Deformable Image Registration

Papież

Szmul

Grau

et al. 2017

Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging

Self Cite

View full text Add to dashboard Cite

Deformable image registration aims to deliver a plausible spatial transformation between two or more images by solving a highly dimensional, ill-posed optimization problem. Covering the complexity of physiological motion has so far been limited to either generic physical models or local motion regularization models. This paper presents an alternative, graphical regularization model, which captures well the non-local scale of motion, and thus enables to incorporate complex regularization models directly into deformable image registration. In order to build the proposed graph-based regularization, a Minimum Spanning Tree (MST), which represents the underlying tissue physiology in a perceptually meaningful way, is computed first. This is followed by a fast non-local cost aggregation algorithm that performs regularization of the estimated displacement field using the precomputed MST. To demonstrate the advantage of the presented regularization, we embed it into the widely used Demons registration framework. The presented method is shown to improve the accuracy for exhale-inhale CT data pairs.

show abstract

Liver Motion Estimation via Locally Adaptive Over-Segmentation Regularization

Cited by 15 publications

References 16 publications

A hybrid optimization strategy for registering images with large local deformations and intensity variations

A hybrid optimization strategy for registering images with large local deformations and intensity variations

Landmark-based evaluation of a deformable motion correction for DCE-MRI of the liver

Non-local Graph-Based Regularization for Deformable Image Registration

Contact Info

Product

Resources

About