Learning a Probabilistic Model for Diffeomorphic Registration

Abstract

We propose to learn a low-dimensional probabilistic deformation model from data which can be used for registration and the analysis of deformations. The latent variable model maps similar deformations close to each other in an encoding space. It enables to compare deformations, generate normal or pathological deformations for any new image or to transport deformations from one image pair to any other image. Our unsupervised method is based on variational inference. In particular, we use a conditional variational autoencoder (CVAE) network and constrain transformations to be symmetric and diffeomorphic by applying a differentiable exponentiation layer with a symmetric loss function. We also present a formulation that includes spatial regularization such as diffusion-based filters. Additionally, our framework provides multi-scale velocity field estimations. We evaluated our method on 3-D intra-subject registration using 334 cardiac cine-MRIs. On this dataset, our method showed state-of-the-art performance with a mean DICE score of 81.2% and a mean Hausdorff distance of 7.3mm using 32 latent dimensions compared to three state-of-the-art methods while also demonstrating more regular deformation fields. The average time per registration was 0.32s. Besides, we visualized the learned latent space and show that the encoded deformations can be used to transport deformations and to cluster diseases with a classification accuracy of 83% after applying a linear projection.

Accepted at (c) IEEE TMI and featured on https://ieee-tmi.org/

References in corpus (12)

• Auto-Encoding Variational Bayes
• Semi-Supervised Learning with Deep Generative Models
• Deeply-Supervised Nets
• An Unsupervised Learning Model for Deformable Medical Image Registration
• Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
• End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training
• Generative Adversarial Networks for MR-CT Deformable Image Registration
• BIRNet: Brain Image Registration Using Dual-Supervised Fully Convolutional Networks
• Parallel transport in shape analysis: a scalable numerical scheme
• Probabilistic Diffeomorphic Registration: Representing Uncertainty

Cited by in corpus (53)

• TransMorph: Transformer for unsupervised medical image registration
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
• SynthMorph: learning contrast-invariant registration without acquired images
• Medical Image Registration Using Deep Neural Networks: A Comprehensive Review
• Improving the generalizability of convolutional neural network-based segmentation on CMR images
• Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates
• 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
• Learning the Effect of Registration Hyperparameters with HyperMorph
• IGCN: Image-to-graph Convolutional Network for 2D/3D Deformable Registration
• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Generating Anthropomorphic Phantoms Using Fully Unsupervised Deformable Image Registration with Convolutional Neural Networks
• Flexible Bayesian Modelling for Nonlinear Image Registration
• Fast GPU 3D Diffeomorphic Image Registration
• Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
• CartiMorph: a framework for automated knee articular cartilage morphometrics
• A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
• Contrastive Registration for Unsupervised Medical Image Segmentation
• Continuous 3D Myocardial Motion Tracking via Echocardiography
• Generative Aging of Brain Images with Diffeomorphic Registration
• Deep learning based registration using spatial gradients and noisy segmentation labels
• Few Labeled Atlases are Necessary for Deep-Learning-Based Segmentation
• SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration
• FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation
• Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• Atlas Based Segmentations via Semi-Supervised Diffeomorphic Registrations
• NeurReg: Neural Registration and Its Application to Image Segmentation
• Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
• Attention for Image Registration (AiR): an unsupervised Transformer approach
• Diffeomorphic Shape Matching by Operator Splitting in 3D Cardiology Imaging
• Unsupervised dynamic modeling of medical image transformation
• A training-free recursive multiresolution framework for diffeomorphic deformable image registration
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow
• Anatomy-Aware Cardiac Motion Estimation
• ProsRegNet: A Deep Learning Framework for Registration of MRI and Histopathology Images of the Prostate
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
• DDR-Net: Dividing and Downsampling Mixed Network for Diffeomorphic Image Registration
• CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
• A Deep Discontinuity-Preserving Image Registration Network
• Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
• CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Network
• Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI
• Deep Learning for Regularization Prediction in Diffeomorphic Image Registration
• Joint cortical registration of geometry and function using semi-supervised learning
• Deformable Image Registration for Self-supervised Cardiac Phase Detection in Multi-View Multi-Disease Cardiac Magnetic Resonance Images
• Multi-phase Deformable Registration for Time-dependent Abdominal Organ Variations
• Privacy Preserving Image Registration
• Online learning in motion modeling for intra-interventional image sequences