An Unsupervised Learning Model for Deformable Medical Image Registration

@article{Balakrishnan2018AnUL,
  title={An Unsupervised Learning Model for Deformable Medical Image Registration},
  author={Guha Balakrishnan and Amy Zhao and Mert Rory Sabuncu and John V. Guttag and Adrian V. Dalca},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={9252-9260}
}
We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. [] Key Method Given a new pair of scans, we can quickly compute a registration field by directly evaluating the function using the learned parameters. We model this function using a CNN, and use a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field.
[PDF] Semantic Reader
445 Citations
Highly Influential Citations
99
Background Citations
174
Methods Citations
225
Results Citations
15

Figures and Tables from this paper

445 Citations

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.

A FCN-based Unsupervised Learning Model for Deformable Chest CT Image Registration

A fast unsupervised learning method for deformable image registration using a fully convolutional network (FCN) that directly learns to estimate a dense displacement vector field (DVF) from a pair of input images.

NeurReg: Neural Registration and Its Application to Image Segmentation

A neural registration framework with a hybrid loss of displacement fields and data similarity is constructed, which substantially improves the current state-of-the-art of registrations and improves registration accuracy with fast inference speed, which can greatly accelerate related medical image analysis tasks.

Supervised deformable image registration using deep neural networks

A supervised method based on a 3D convolutional neural network, that learns to estimate registration errors from a pair of image patches, that can train the network to robustly estimateRegistration errors in a predetermined range, with sub-voxel accuracy is proposed.

Metric Learning for Image Registration

This work embeds a deep learning model in an optimization-based registration algorithm to parameterize and data-adapt the registration model itself, allowing controlling the desired level of regularity and preserving structural properties of a registration model.

Unsupervised deformable image registration network for 3D medical images

The proposed UDIR-Net is designed in an encoder-decoder architecture and directly estimates the complex deformation field between input pairwise images without any supervised information, and designs a novel hierarchical loss function that evaluates multiscale similarity loss between registered image pairs.

Unsupervised deformable image registration network for 3D medical images

The proposed UDIR-Net is designed in an encoder-decoder architecture and directly estimates the complex deformation field between input pairwise images without any supervised information, and designs a novel hierarchical loss function that evaluates multiscale similarity loss between registered image pairs.

Two-Stage Unsupervised Learning Method for Affine and Deformable Medical Image Registration

This work proposes a two-stage unsupervised learning method for 3D medical image registration that outperforms several state-of-the-art methods in terms of accuracy and efficiency.

Medical Image Registration via Neural Fields

Experiments demonstrate that NIR yields state-of-the-art performance in terms of both registration accuracy and regularity, while running significantly faster than traditional optimization-based methods.

Learning Deformable Registration of Medical Images with Anatomical Constraints

...

References

SHOWING 1-10 OF 46 REFERENCES

SVF-Net: Learning Deformable Image Registration Using Shape Matching

An innovative approach for registration based on the deterministic prediction of the parameters from both images instead of the optimization of a energy criteria is proposed and shows an important improvement over a state of the art optimization based algorithm.

Non-rigid image registration using fully convolutional networks with deep self-supervision

A novel non-rigid image registration algorithm that is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered that has been evaluated for registering 3D structural brain magnetic resonance (MR) images and obtained better performance than state-of-the-art image registration algorithms.

Patch-Based Discrete Registration of Clinical Brain Images

A non-rigid registration method for aligning brain images acquired in clinical settings that outperforms state of the art registration algorithms and avoids catastrophic failures often caused by these images.

End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network

The results demonstrate that registration with DIRNet is as accurate as a conventional deformable image registration method with short execution times.

Dense image registration through MRFs and efficient linear programming

Nonrigid registration using free-form deformations: application to breast MR images

The results clearly indicate that the proposed nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.

HAMMER: hierarchical attribute matching mechanism for elastic registration

A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain, where it results in accurate superposition of image data from individuals with significant anatomical differences.

Quicksilver: Fast predictive image registration – A deep learning approach

Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration

A fast diffeomorphic image registration algorithm