SynthMorph: learning contrast-invariant registration without acquired images

Abstract

We introduce a strategy for learning image registration without acquired imaging data, producing powerful networks agnostic to contrast introduced by magnetic resonance imaging (MRI). While classical registration methods accurately estimate the spatial correspondence between images, they solve an optimization problem for every new image pair. Learning-based techniques are fast at test time but limited to registering images with contrasts and geometric content similar to those seen during training. We propose to remove this dependency on training data by leveraging a generative strategy for diverse synthetic label maps and images that exposes networks to a wide range of variability, forcing them to learn more invariant features. This approach results in powerful networks that accurately generalize to a broad array of MRI contrasts. We present extensive experiments with a focus on 3D neuroimaging, showing that this strategy enables robust and accurate registration of arbitrary MRI contrasts even if the target contrast is not seen by the networks during training. We demonstrate registration accuracy surpassing the state of the art both within and across contrasts, using a single model. Critically, training on arbitrary shapes synthesized from noise distributions results in competitive performance, removing the dependency on acquired data of any kind. Additionally, since anatomical label maps are often available for the anatomy of interest, we show that synthesizing images from these dramatically boosts performance, while still avoiding the need for real intensity images. Our code is available at https://w3id.org/synthmorph.

16 pages, 15 figures, 3 tables, deformable image registration, data independence, deep learning, MRI-contrast invariance, anatomy agnosticism, final published version

References in corpus (1)

• Learning Deformable Registration of Medical Images with Anatomical Constraints

Cited by in corpus (17)

• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Generative Aging of Brain Images with Diffeomorphic Registration
• SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
• Supervision by Denoising for Medical Image Segmentation
• A deformation-based morphometry framework for disentangling Alzheimer's disease from normal aging using learned normal aging templates
• Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registration
• Learning accurate rigid registration for longitudinal brain MRI from synthetic data
• MBSS-T1: Model-Based Subject-Specific Self-Supervised Motion Correction for Robust Cardiac T1 Mapping
• Domain-randomized deep learning for neuroimage analysis
• Gaussian Primitives for Deformable Image Registration
• 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
• Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transport
• SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions
• CT respiratory motion synthesis using joint supervised and adversarial learning
• Deep infant brain segmentation from multi-contrast MRI
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• Data-driven registration and modeling of brain deformation for image-guided neurosurgery