VoxelMorph: A Learning Framework for Deformable Medical Image Registration

By Guha Balakrishnan, Amy Zhao, Mert Rory Sabuncu, John V. Guttag, Adrian V. Dalca. IEEE Transactions on Medical Imaging, 2018

2,150 citations recorded by the source corpus.

We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this paper, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications. Our code is freely available at https://github.com/voxelmorph/voxelmorph.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6a88c8abd298b5e9ea7485f41a6a1b1e43b16d5f

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep learning in medical image registration: a review (2019, methodology): “[181] Brain 3D-3D No MR Deformable [5, 6, 21] Brain 3D-3D No MR Deformable”
SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, background): “Recently, VoxelMorph [64] introduces the deep neural network to estimate the cross-modal ﬂow with no supervision, which only employs NCC as the loss function.”
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, methodology): “Balakrishnan et al. [16], [27] presented a pairwise 3D medical image registration algorithm using a CNN with a spatial transform layer (STL), which parameters are learned by the normalized cross-correlation function.”
Deep learning in medical image registration: a survey (2019, methodology): “[7, 8] proposed a general framework for unsupervised image registration, which can be either unimodal or multimodal theoretically.”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, methodology): “Building on the successful demonstration of these methods, several recent papers [9, 10, 23, 22, 44] explore unsupervised, or end-to-end, strategies.”
Transformers in Medical Image Analysis: A Review (2022, methodology): “Inspired by the architecture of TransUnet [68], they proposed ViT-V-Net [29], which combines ViT and V-Net by simply altering the network architecture of VoxelMorph (a conventional registration network) [131].”
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].”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “[132] propose a method for unsupervised image registration, which attempts to directly compute the deformation field.”
TransMorph: Transformer for unsupervised medical image registration (2021, positive): “Here, we used a method similar to that described in (Balakrishnan et al. 2019), in which we designed s f and sm as image volumes with K channels, each channel containing a binary mask defining the segmentation of a specific structure/organ.”
A Survey of Deep Learning for Scientific Discovery (2020, methodology): “The code for this and several followup papers [13, 39] provides a helpful example for building oﬀ of and applying these methods https://github . com/voxelmorph/voxelmorph .”