Topology Preservation and Anatomical Feasibility in Random Walker Image Registration

Andrews, Shawn; Tang, Lisa; Hamarneh, Ghassan

doi:10.1007/978-3-319-10404-1_27

Cited by 6 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To specifically tackle the challenge of weight tuning in DIR, techniques for adaptively determining the weight associated with the smoothness term that regularizes the transformation during the optimization process have been proposed, Andrews et al (2014) and Cahill et al (2009). The focus of such approaches was more on accomodating the absence of information (e.g.…”

Section: Related Workmentioning

confidence: 99%

The feasibility of manual parameter tuning for deformable breast MR image registration from a multi-objective optimization perspective

et al. 2017

View full text Add to dashboard Cite

Deformable image registration is typically formulated as an optimization problem involving a linearly weighted combination of terms that correspond to objectives of interest (e.g. similarity, deformation magnitude). The weights, along with multiple other parameters, need to be manually tuned for each application, a task currently addressed mainly via trial-and-error approaches. Such approaches can only be successful if there is a sensible interplay between parameters, objectives, and desired registration outcome. This, however, is not well established. To study this interplay, we use multi-objective optimization, where multiple solutions exist that represent the optimal trade-offs between the objectives, forming a so-called Pareto front. Here, we focus on weight tuning. To study the space a user has to navigate during manual weight tuning, we randomly sample multiple linear combinations. To understand how these combinations relate to desirability of registration outcome, we associate with each outcome a mean target registration error (TRE) based on expert-defined anatomical landmarks. Further, we employ a multi-objective evolutionary algorithm that optimizes the weight combinations, yielding a Pareto front of solutions, which can be directly navigated by the user. To study how the complexity of manual weight tuning changes depending on the registration problem, we consider an easy problem, prone-to-prone breast MR image registration, and a hard problem, prone-to-supine breast MR image registration. Lastly, we investigate how guidance information as an additional objective influences the prone-to-supine registration outcome. Results show that the interplay between weights, objectives, and registration outcome makes manual weight tuning feasible for the prone-to-prone problem, but very challenging for the harder prone-to-supine problem. Here, patient-specific, multi-objective weight optimization is needed, obtaining a mean TRE of 13.6 mm without guidance information reduced to 7.3 mm with guidance information, but also providing a Pareto front that exhibits an intuitively sensible interplay between weights, objectives, and registration outcome, allowing outcome selection.

show abstract

Section: Related Workmentioning

confidence: 99%

The feasibility of manual parameter tuning for deformable breast MR image registration from a multi-objective optimization perspective

et al. 2017

View full text Add to dashboard Cite

show abstract

“…We achieved this by performing probabilistic graph-labeling in the common space using a labelset of coupled pairs. Future research directions include using parallel computing to speed up all calculations and exploring the potential advantages of incorporating the method of [8] to enforce additional topology-preserving constraints on the update fields during optimization. Fig.…”

Section: Discussionmentioning

confidence: 99%

“…Soon after its first adoption for stereo-correspondence [2], it was also deployed for medical image registration [1], leading to the random walker image registration algorithm (RWIR), which has since been evolving via various extensions that are either aimed at decreasing its computational complexity or improving its accuracy [3]- [8]. Empirical results reported in these extensions [3]- [8] all suggest that RWIR can be advanced to an accurate, efficient, and well-validated tool for practical real clinical applications.…”

Section: Introductionmentioning

confidence: 99%

“…While often overlooked, inverse consistency is an important criterion to consider, in addition to registration accuracy and other criteria like smoothness and invertibility of the solution [6], [8]. For instance, in image-guided and adaptive radiation therapy applications [9], where pre-therapy and daily CT images are co-registered, inverse consistent registrations will ensure that a pair of symmetric transformations can be obtained so that changes in radiation dose as captured by these images are invariant to changes in the reference frame.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Random walker image registration with inverse consistency

Tang

Andrews

Hamarneh

2015

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)

Self Cite

View full text Add to dashboard Cite

One important property of a registration solution is inverse consistency. While often overlooked, this property is critical in many medical applications, including radiationtherapy treatment planning and unbiased atlas-construction. In this paper, we propose a novel extension to the graphbased random walker image registration (RWIR) algorithm to ensure its inverse consistency. In contrast to many existing inverse-consistent algorithms, where two bi-directional transformations are independently sought and subsequently averaged, we calculate both transformations simultaneously by performing a constrained graph labeling in a common domain onto which both images are mapped, and employ a set of coupled labels so that both transformations are computed within a single optimization step. As our results on synthetic and real problems involving cardiac, thigh and brain images demonstrate, our method not only improved inverse consistency of RWIR, but also statistically significantly improved its accuracy. Comparison to another state-of-theart symmetric algorithm on various datasets also gave highly encouraging results.

show abstract

“…This has prompted the development of image registration methods with topology-preservation, e.g. [8]. In this work, we borrow and adapt the topology preservation idea for the PSL matching problem.…”

Section: Introductionmentioning

confidence: 99%

Skin lesion matching using Jacobian based descriptors for topology preservation

Mirzaalian

Lee

Hamarneh

2015

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)

Self Cite

View full text Add to dashboard Cite

Developing an automatic system for tracking pigmented skin lesions (PSL) is important for early skin cancer detection. PSL tracking is typically formulated as finding correspondences in an optimization framework. When lesions are close to each other, it becomes likely to mis-correspond a PSL with nearby ones. To alleviate this problem, we introduce a novel topology-preservation concept based on which we derive different energy terms for the PSL matching objective function. Given two graph-represented sets of PSLs to correspond, in addition to unary and binary energy terms, we quantify topological-preservation using a Jacobian-like matrix capturing how triplets of vertices in one graph match another triplet in the other graph. We validate the goodness of our proposed descriptors on 97 pairs of human back digital color images. The results indicate that our new descriptors improve the PSL matching accuracy by over 9%.

show abstract

Topology Preservation and Anatomical Feasibility in Random Walker Image Registration

Cited by 6 publications

References 14 publications

The feasibility of manual parameter tuning for deformable breast MR image registration from a multi-objective optimization perspective

The feasibility of manual parameter tuning for deformable breast MR image registration from a multi-objective optimization perspective

Random walker image registration with inverse consistency

Skin lesion matching using Jacobian based descriptors for topology preservation

Contact Info

Product

Resources

About