Anatomy-aware and acquisition-agnostic joint registration with SynthMorph

Abstract

Affine image registration is a cornerstone of medical image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function that maps an image pair to an output transform. Evaluating the function is fast, but capturing large transforms can be challenging, and networks tend to struggle if a test-image characteristic shifts from the training domain, such as resolution. Most affine methods are agnostic to the anatomy the user wishes to align, meaning the registration will be inaccurate if algorithms consider all structures in the image. We address these shortcomings with SynthMorph, a fast, symmetric, diffeomorphic, and easy-to-use DL tool for joint affine-deformable registration of any brain image without preprocessing. First, we leverage a strategy that trains networks with widely varying images synthesized from label maps, yielding robust performance for image types unseen at training. Second, we optimize the spatial overlap of select anatomical labels. This enables networks to distinguish anatomy of interest from irrelevant structures, removing the need for preprocessing that excludes content that may impinge on anatomy-specific registration. Third, we combine the affine model with a deformable hypernetwork that lets users choose the optimal deformation-field regularity for their specific data, at registration time, in a fraction of the time required by classical methods. We analyze how competing architectures learn affine transforms and compare state-of-the-art registration tools across an extremely diverse set of neuroimaging data, aiming to truly capture the behavior of methods in the real world. SynthMorph demonstrates high accuracy and is available at https://w3id.org/synthmorph, as a single complete end-to-end solution for registration of brain MRI.

33 pages, 19 figures, 4 tables, affine registration, deformable registration, deep learning, hypernetwork, domain shift, neuroimaging, final published version

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Point-Set Registration: Coherent Point Drift
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Deep Visual Domain Adaptation: A Survey
• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• Deep Learning in Medical Image Registration: A Review
• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• SynthStrip: Skull-Stripping for Any Brain Image
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
• Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
• Learning a Probabilistic Model for Diffeomorphic Registration
• SynthMorph: learning contrast-invariant registration without acquired images
• More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
• Non-rigid image registration using fully convolutional networks with deep self-supervision
• A Learning Strategy for Contrast-agnostic MRI Segmentation
• Generative Adversarial Networks for MR-CT Deformable Image Registration
• Learning the Effect of Registration Hyperparameters with HyperMorph
• Boosting Skull-Stripping Performance for Pediatric Brain Images
• Rapid head-pose detection for automated slice prescription of fetal-brain MRI
• SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI

Cited by in corpus (5)

• Boosting Skull-Stripping Performance for Pediatric Brain Images
• Domain-randomized deep learning for neuroimage analysis
• FetDTIAlign: A Deep Learning Framework for Affine and Deformable Registration of Fetal Brain dMRI
• Learning accurate rigid registration for longitudinal brain MRI from synthetic data
• Deep infant brain segmentation from multi-contrast MRI