Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration

Krebs, Julian; Mansi, Tommaso; Mailhé, Boris; Ayache, Nicholas; Delingette, Hervé

doi:10.1007/978-3-030-00889-5_12

Cited by 52 publications

(56 citation statements)

References 9 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the probabilistic model, we estimate F i z by maximizing the posterior registration probability p(F i z |F i x ; F i y ) from the observed F i x and F i y . Similar to other works [4,12], we adopt a variational approach to compute p(F i z |F i x ; F i y ) by first introducing an approximate posterior probability q ψ (F i z |F i x ; F i y ) and then minimizing a KL divergence between p(F i z |F i x ; F i y ) and q ψ (F i z |F i x ; F i y ) to make these two distributions as similar as possible.…”

Section: Feature-level Probabilistic Modelsupporting

confidence: 83%

Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Liu

Zhu

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Brain image registration transforms a pair of images into one system with the matched imaging contents, which is of essential importance for brain image analysis. This paper presents a novel framework for unsupervised 3D brain image registration by capturing the feature-level transformation relationships between the unaligned image and reference image. To achieve this, we develop a feature-level probabilistic model to provide the direct regularization to the hidden layers of two deep convolutional neural networks, which are constructed from two input images. This model design is developed into multiple layers of these two networks to capture the transformation relationships at different levels. We employ two common benchmark datasets for 3D brain image registration and perform various experiments to evaluate our method. Experimental results show that our method clearly outperforms state-of-the-art methods on both benchmark datasets by a large margin.

show abstract

Section: Feature-level Probabilistic Modelsupporting

confidence: 83%

Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Liu

Zhu

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In our work, we bridge these two paradigms to offer classical guarantees within a machine learning approach. We note the contemporaneous development of a method that uses a conditional variational auto encoder (CVAE) to learn diffeomorphic representations [43,41]. Similar to our method, this approach uses a variational strategy to learn a network to predict a stationary velocity field (SVF).…”

Section: Learning-based Registrationmentioning

confidence: 99%

Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces

Dalca

Balakrishnan

Guttag

et al. 2019

Medical Image Analysis

274

210

View full text Add to dashboard Cite

Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we build a connection between classical and learning-based methods. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task for both images and anatomical surfaces, and provide extensive empirical analyses. Our principled approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees. Our implementation is available at http://voxelmorph.csail.mit.edu.Keywords medical image registration · diffeomorphic registration · invertible registration · probabilistic modeling · convolutional neural networks · variational inference · machine learning arXiv:1903.03545v2 [cs.CV] 23 Jul 2019 experiments, we add baselines, new experiments on registration of both images and surfaces, and provide an analysis of the effect of our diffeomorphic implementation on field regularity and runtime. We implement our method as part of the registration framework called VoxelMorph, which is available at http://voxelmorph.csail.mit.edu. Related Works Classical Registration MethodsClassical methods solve an optimization over the space of deformations [5,7,8,11,19,28,66,69,70]. Common representations are displacement vector fields, including elastic-type models [8,21,62], free-form deformations with b-splines [61], statistical parametric mapping [6], Demons [56,66], and more recently discrete methods [19,30,28].Constraining the allowable transformations to diffeomorphisms ensures certain desirable properties, such as preservation of topology. Diffeomorphic transforms have seen extensive methodological development, yielding state-ofthe-art tools, such as Large Diffeomorphic Distance Metric Mapping (LDDMM) [11,14,15,32,37,49,55,70], DARTEL [5], diffeomorphic Demons [67], and symmetric normalization (SyN) [7]. In general, these tools demand substantial time and computational resources for a given image pair.Some recent GPU-based iterative algorithms use these frameworks to develop faster algorithms by requiring a GPU to be available for each registration [51,50]. Recent learning-based registration methods have demonstrated that they can provide good initializations to iterative GPU methods [10] to further improve runtime.

show abstract

“…VoxelMorph, proposed by Balakrishnan et al [23], [24], is an unsupervised learning-based method for 3D medical image registration that predicts a dense deformation field. Another recently proposed unsupervised method by Krebs et al [25], [26], based on a low-dimensional probablistic model, performs comparably to VoxelMorph. VoxelMorph contains an encoderdecoder structure, uses warping operation to produce warped moving images, and is trained to minimize the dissimilarity between the warped image and the fixed image.…”

Section: Unsupervised Learning Methodsmentioning

confidence: 99%

Unsupervised 3D End-to-End Medical Image Registration With Volume Tweening Network

Zhao

Lau

Luo

et al. 2020

IEEE J. Biomed. Health Inform.

218

180

View full text Add to dashboard Cite

3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing), which are very difficult to obtain. Unsupervised learning methods ease the burden of manual annotation by exploiting unlabeled data without supervision. In this paper, we propose a new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), for 3D medical image registration. We propose three innovative technical components: (1) An end-to-end cascading scheme that resolves large displacement;(2) An efficient integration of affine registration network; and (3) An additional invertibility loss that encourages backward consistency. Experiments demonstrate that our algorithm is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-theart performance in medical image registration.

show abstract

Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration

Cited by 52 publications

References 9 publications

Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces

Unsupervised 3D End-to-End Medical Image Registration With Volume Tweening Network

Contact Info

Product

Resources

About