Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

Abstract

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 http://voxelmorph.csail.mit.edu .

arXiv commentMICCAI 2018 (Oral Presentation). Proceedings: LNCS 11070, pp 729-738

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• An Unsupervised Learning Model for Deformable Medical Image Registration
• End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
• Non-rigid image registration using fully convolutional networks with deep self-supervision

Cited by in corpus (63)

• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• Deep Learning in Medical Image Registration: A Review
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Learning a Probabilistic Model for Diffeomorphic Registration
• Medical Image Registration Using Deep Neural Networks: A Comprehensive Review
• 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
• Learning Conditional Deformable Templates with Convolutional Networks
• QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
• Data augmentation using learned transformations for one-shot medical image segmentation
• Cortical surface registration using unsupervised learning
• 3D Convolutional Neural Networks Image Registration Based on Efficient Supervised Learning from Artificial Deformations
• Enhancing Medical Image Registration via Appearance Adjustment Networks
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• Is Image-to-Image Translation the Panacea for Multimodal Image Registration? A Comparative Study
• Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
• Deform-GAN:An Unsupervised Learning Model for Deformable Registration
• NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach
• AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes
• Cross-Modality Image Registration using a Training-Time Privileged Third Modality
• CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration
• Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
• Contrastive Registration for Unsupervised Medical Image Segmentation
• Networks for Joint Affine and Non-parametric Image Registration
• A Two-Step Deep Learning Method for 3DCT-2DUS Kidney Registration During Breathing
• Deep learning based registration using spatial gradients and noisy segmentation labels
• Spatiotemporal PET reconstruction using ML-EM with learned diffeomorphic deformation
• Co-Learning Semantic-aware Unsupervised Segmentation for Pathological Image Registration
• Leveraging Unsupervised Image Registration for Discovery of Landmark Shape Descriptor
• SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration
• IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data
• Semantic similarity metrics for learned image registration
• Registration of serial sections: An evaluation method based on distortions of the ground truths
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
• Neural Multi-Scale Self-Supervised Registration for Echocardiogram Dense Tracking
• Region-specific Diffeomorphic Metric Mapping
• Biomechanical modelling of brain atrophy through deep learning
• Test-Time Training for Deformable Multi-Scale Image Registration
• NeurReg: Neural Registration and Its Application to Image Segmentation
• Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
• A training-free recursive multiresolution framework for diffeomorphic deformable image registration
• Deformable Registration Using Average Geometric Transformations for Brain MR Images
• Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images
• An Auto-Encoder Strategy for Adaptive Image Segmentation
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
• InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration
• ProsRegNet: A Deep Learning Framework for Registration of MRI and Histopathology Images of the Prostate
• Deep Morphological Simplification Network (MS-Net) for Guided Registration of Brain Magnetic Resonance Images
• Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
• Diffeomorphic Transformations for Time Series Analysis: An Efficient Approach to Nonlinear Warping
• Dense Deformation Network for High Resolution Tissue Cleared Image Registration
• Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations
• DDR-Net: Dividing and Downsampling Mixed Network for Diffeomorphic Image Registration
• DeepSim: Semantic similarity metrics for learned image registration
• Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling
• Joint cortical registration of geometry and function using semi-supervised learning
• Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas
• Spot the Difference: Detection of Topological Changes via Geometric Alignment
• Are Registration Uncertainty and Error Monotonically Associated
• On the Applicability of Registration Uncertainty
• Diffusion tensor driven image registration: a deep learning approach