Fast GPU 3D diffeomorphic image registration

Brunn, Malte; Himthani, Naveen; Biros, George; Mehl, Miriam; Mang, Andreas

doi:10.1016/j.jpdc.2020.11.006

Cited by 23 publications

(68 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The source code has been recently released with [17]. A GPU optimized implementation of the method is being proposed in the ArXiv paper [4].…”

Section: Computational Complexity Due To Pde Integrationmentioning

confidence: 99%

Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM

Hernández

2021

J Math Imaging Vis

View full text Add to dashboard Cite

The family of PDE-constrained Large Deformation Diffeomorphic Metric Mapping (LDDMM) methods is emerging as a particularly interesting approach for physically meaningful diffeomorphic transformations. The original combination of Gauss-Newton-Krylov optimization and Runge-Kutta integration shows excellent numerical accuracy and fast convergence rate. However, its most significant limitation is the huge computational complexity, hindering its extensive use in Computational Anatomy applied studies. This limitation has been treated independently by the problem formulation in the space of band-limited vector fields and semi-Lagrangian integration. The purpose of this work is to combine both in three variants of band-limited PDE-constrained LDDMM for further increasing their computational efficiency. The accuracy of the resulting methods is evaluated extensively. For all the variants, the proposed combined approach shows a significant increment of the computational efficiency. In addition, the variant based on the deformation state equation is positioned consistently as the best performing method across all the evaluation frameworks in terms of accuracy and efficiency.

show abstract

“…The source code has been recently released with [17]. A GPU optimized implementation of the method is being proposed in the ArXiv paper [4].…”

Section: Computational Complexity Due To Pde Integrationmentioning

confidence: 99%

Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM

Hernández

2021

J Math Imaging Vis

View full text Add to dashboard Cite

show abstract

“…But unfortunately, these often come at a high computational price: to register complex shapes, quasi-Newton optimizers require dozens of evaluations of the deformation model Morph(θ, x) and of its gradients. In practice, fitting a complex model to a pair of high-resolution shapes may thus take several minutes or seconds [17]. This precludes real-time processing and hinders research on advanced deformation models.…”

Section: Robot: a Convenient Representation Of The Optimal Transport ...mentioning

confidence: 99%

“…Shape registration is a fundamental but difficult problem in computer vision. The task is to determine plausible spatial correspondences between pairs of shapes, with use cases that range from pose estimation for noisy point clouds [14] to the nonparametric registration of high-resolution medical images [17]. As illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

Accurate Point Cloud Registration with Robust Optimal Transport

Shen

Feydy

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

This work investigates the use of robust optimal transport (OT) for shape matching. Specifically, we show that recent OT solvers improve both optimization-based and deep learning methods for point cloud registration, boosting accuracy at an affordable computational cost. This manuscript starts with a practical overview of modern OT theory. We then provide solutions to the main difficulties in using this framework for shape matching. Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration. Our OT-based methods achieve state-of-the-art results on Kitti and for the challenging lung registration task, both in terms of accuracy and scalability. We also release PVT1010, a new public dataset of 1,010 pairs of lung vascular trees with densely sampled points. This dataset provides a challenging use case for point cloud registration algorithms with highly complex shapes and deformations. Our work demonstrates that robust OT enables fast pre-alignment and fine-tuning for a wide range of registration models, thereby providing a new key method for the computer vision toolbox. Our code and dataset are available online at: https://github.com/uncbiag/robot.

show abstract

“…Furthermore, the metric induced by the diffeomorphism can be used as an alternative over point-to-point distances. State of the art iterative techniques include DARTEL [3], Diffeomorphic Demons [26] and LDDMM [5,7] on volumetric images, with LDDMM also being generalised to surfaces [25]. Deformetrica [6] is an open-source implementation of a specific instance of LDDMM that makes use of control points, it is applicable to many representations.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Diffeomorphic Surface Registration and Non-linear Modelling

Croquet

Christiaens

Weinberg

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

View full text Add to dashboard Cite

Registration is an essential tool in image analysis. Deep learning based alternatives have recently become popular, achieving competitive performance at a faster speed. However, many contemporary techniques are limited to volumetric representations, despite increased popularity of 3D surface and shape data in medical image analysis. We propose a one-step registration model for 3D surfaces that internalises a lower dimensional probabilistic deformation model (PDM) using conditional variational autoencoders (CVAE). The deformations are constrained to be diffeomorphic using an exponentiation layer. The one-step registration model is benchmarked against iterative techniques, trading in a slightly lower performance in terms of shape fit for a higher compactness. We experiment with two distance metrics, Chamfer distance (CD) and Sinkhorn divergence (SD), as specific distance functions for surface data in real-world registration scenarios. The internalised deformation model is benchmarked against linear principal component analysis (PCA) achieving competitive results and improved generalisability from lower dimensions.

show abstract

Fast GPU 3D diffeomorphic image registration

Cited by 23 publications

References 72 publications

Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM

Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM

Accurate Point Cloud Registration with Robust Optimal Transport

Unsupervised Diffeomorphic Surface Registration and Non-linear Modelling

Contact Info

Product

Resources

About