An Unsupervised Learning Model for Deformable Medical Image Registration

Abstract

We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. Current registration methods optimize an objective function independently for each pair of images, which can be time-consuming for large data. We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest. 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 convolutional neural network (CNN), and use a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field. The proposed method does not require supervised information such as ground truth registration fields or anatomical landmarks. We demonstrate registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Our method promises to significantly speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is available at https://github.com/balakg/voxelmorph .

9 pages, in CVPR 2018

References in corpus (1)

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

Cited by in corpus (46)

• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• An overview of deep learning in medical imaging focusing on MRI
• Diffusion Models in Vision: A Survey
• TransMorph: Transformer for unsupervised medical image registration
• Deep Learning in Medical Image Registration: A Review
• Deep Learning in Medical Image Registration: A Survey
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• Recursive Cascaded Networks for Unsupervised Medical Image Registration
• Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
• Learning a Probabilistic Model for Diffeomorphic Registration
• Learning Deformable Registration of Medical Images with Anatomical Constraints
• A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• mlVIRNET: Multilevel Variational Image Registration Network
• LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging
• Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
• Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
• From Screens to Scenes: A Survey of Embodied AI in Healthcare
• When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)
• UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration
• Generating Anthropomorphic Phantoms Using Fully Unsupervised Deformable Image Registration with Convolutional Neural Networks
• deepPERFECT: Novel Deep Learning CT Synthesis Method for Expeditious Pancreatic Cancer Radiotherapy
• FDRN: A Fast Deformable Registration Network for Medical Images
• NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach
• Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networks
• Transformer Lesion Tracker
• Cross-Modality Image Registration using a Training-Time Privileged Third Modality
• Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
• 3D Brain and Heart Volume Generative Models: A Survey
• Recursive Deformable Image Registration Network with Mutual Attention
• Segmentation by Test-Time Optimization (TTO) for CBCT-based Adaptive Radiation Therapy
• AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
• ConKeD: Multiview contrastive descriptor learning for keypoint-based retinal image registration
• INSPIRE: Intensity and spatial information-based deformable image registration
• Deformation-Aware Segmentation Network Robust to Motion Artifacts for Brain Tissue Segmentation using Disentanglement Learning
• ERNet: Unsupervised Collective Extraction and Registration in Neuroimaging Data
• Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields
• RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration
• ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration
• A training-free recursive multiresolution framework for diffeomorphic deformable image registration
• InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration
• One-shot Joint Extraction, Registration and Segmentation of Neuroimaging Data
• Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
• Deformable Image Registration for Self-supervised Cardiac Phase Detection in Multi-View Multi-Disease Cardiac Magnetic Resonance Images