Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

By Adrian V. Dalca, Guha Balakrishnan, John V. Guttag, Mert Rory Sabuncu. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2018

415 citations recorded by the source corpus.

Traditional 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 present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task, and provide an empirical analysis of the algorithm. Our approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees and uncertainty estimates. Our implementation is available online at this http URL .

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/741aa5422871259949d3a2dd16ed727a1fd63e67

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, background): “Although Dalca et al. [29] introduced a diffeomorphic integration layers to address this issue, the constraint should be also applied at the inference phase, which incurs additional complexity.”
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation (2019, methodology): “This mature field spans optimization-based methods [4, 7, 67, 70], and recent learning-based methods [8, 9, 20, 42, 62, 72, 80].”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, background): “This paper extends a preliminary version of this work presented at the Medical Image Computing and Computer Assisted Intervention (MICCAI) 2018 conference [18].”
Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks (2020, methodology): “Baseline Methods We compare our method with two conventional approaches (denoted as Demons [27] and SyN [2]) and two cutting edge DLIR methods (denoted as VM[4] and DIF-VM [5]).”
Deep learning in medical image registration: a survey (2019, background): “In a follow-up paper, Dalca et al. [23] casted deformation prediction as variational inference.”
Diffusion models in medical imaging: A comprehensive survey (2022, methodology): “Figure 12: Visual comparison of DDM [68], VM [120], and VM-Diff [121] for generating temporal cardiac images.”