Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces

Abstract

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.

MedIA: Medical Image Analysis (MICCAI2018 Special Issue). Expands on MICCAI 2018 paper (arXiv:1805.04605) by introducing an extension to anatomical surface registration, new experiments, and analysis of diffeomorphic implementations. Keywords: medical image registration; diffeomorphic; invertible; probabilistic modeling; variational inference. Code available at http://voxelmorph.csail.mit.edu. arXiv admin note: text overlap with arXiv:1805.04605

References in corpus (3)

• Domain-adversarial neural networks to address the appearance variability of histopathology images
• Learning a Probabilistic Model for Diffeomorphic Registration
• Non-rigid image registration using fully convolutional networks with deep self-supervision

Cited by in corpus (63)

• TransMorph: Transformer for unsupervised medical image registration
• SynthMorph: learning contrast-invariant registration without acquired images
• A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint
• Learning Conditional Deformable Templates with Convolutional Networks
• Medical image registration using unsupervised deep neural network: A scoping literature review
• Cortical surface registration using unsupervised learning
• Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration
• Learning the Effect of Registration Hyperparameters with HyperMorph
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
• AutoFuse: Automatic Fusion Networks for Deformable Medical Image Registration
• Enhancing Medical Image Registration via Appearance Adjustment Networks
• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learning
• Generating Anthropomorphic Phantoms Using Fully Unsupervised Deformable Image Registration with Convolutional Neural Networks
• One shot PACS: Patient specific Anatomic Context and Shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTs
• 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
• CartiMorph: a framework for automated knee articular cartilage morphometrics
• A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
• Volumetric landmark detection with a multi-scale shift equivariant neural network
• Deep Learning based Direct Segmentation Assisted by Deformable Image Registration for Cone-Beam CT based Auto-Segmentation for Adaptive Radiotherapy
• Mutual information neural estimation for unsupervised multi-modal registration of brain images
• Generative Aging of Brain Images with Diffeomorphic Registration
• Brain Tumor Sequence Registration with Non-iterative Coarse-to-fine Networks and Dual Deep Supervision
• Segmentation by Test-Time Optimization (TTO) for CBCT-based Adaptive Radiation Therapy
• ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
• Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound
• Few Labeled Atlases are Necessary for Deep-Learning-Based Segmentation
• Deformable image registration with deep network priors: a study on longitudinal PET images
• Deep learning based CT-to-CBCT deformable image registration for autosegmentation in head and neck adaptive radiation therapy
• An Auto-Context Deformable Registration Network for Infant Brain MRI
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data
• Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer
• Atlas Based Segmentations via Semi-Supervised Diffeomorphic Registrations
• ModeTv2: GPU-accelerated Motion Decomposition Transformer for Pairwise Optimization in Medical Image Registration
• Diffeomorphic Shape Matching by Operator Splitting in 3D Cardiology Imaging
• Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
• Unsupervised Method for Intra-patient Registration of Brain Magnetic Resonance Images based on Objective Function Weighting by Inverse Consistency: Contribution to the BraTS-Reg Challenge
• Propagation and Attribution of Uncertainty in Medical Imaging Pipelines
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• A low-rank representation for unsupervised registration of medical images
• MBSS-T1: Model-Based Subject-Specific Self-Supervised Motion Correction for Robust Cardiac T1 Mapping
• RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration
• Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transport
• InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration
• Eddeep: Fast eddy-current distortion correction for diffusion MRI with deep learning
• Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
• An explainable framework for the relationship between dementia and glucose metabolism patterns
• CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
• A Deep Discontinuity-Preserving Image Registration Network
• MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation
• Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
• Learning unbiased group-wise registration (LUGR) and joint segmentation: evaluation on longitudinal diffusion MRI
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration
• Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration
• Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling
• Regional Deep Atrophy: a Self-Supervised Learning Method to Automatically Identify Regions Associated With Alzheimer's Disease Progression From Longitudinal MRI
• POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration
• Deformable Image Registration for Self-supervised Cardiac Phase Detection in Multi-View Multi-Disease Cardiac Magnetic Resonance Images
• Online learning in motion modeling for intra-interventional image sequences
• Multi-phase Deformable Registration for Time-dependent Abdominal Organ Variations
• Joint Optical Neuroimaging Denoising with Semantic Tasks