DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling

• URL: http://arxiv.org/abs/2606.30183v1
• Date: Mon, 29 Jun 2026 11:57:51 GMT
• Title: DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling
• Abstract summary: We propose a novel DrivenMorph framework that bridges attention mechanisms with variational image registration.<n>The resulting driving force, computed from local differences in the latent feature space, provides explicit semantic guidance throughout the registration process.<n>Our approach not only integrates traditional registration principles with popular deep networks, but also separates difference modeling from deformation.
• Score: 3.57050501208186
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical image registration benefits significantly from deep learning, yet existing approaches often lack physical explainability and fine-grained deformation control. Motivated by Demons algorithms, we propose a novel DrivenMorph framework that bridges attention mechanisms with variational image registration by incorporating difference modeling as a physically inspired inductive bias. The resulting driving force, computed from local differences in the latent feature space, provides explicit semantic guidance throughout the registration process. It directly drives the registration process through a neural Demons layer that simulates force-displacement interactions to generate smooth and anatomically consistent deformation. Unlike previous methods, our approach not only integrates traditional registration principles with popular deep networks, providing an explainable and efficient solution for learning-based medical image registration, but also separates difference modeling from deformation, improving modularity and explainability. Extensive experiments on multiple 3D brain MRI datasets demonstrate superior performance over state of-the-art learning-based and optimization-based methods. Furthermore, visualizations and statistical analyses confirm that the learned driving force aligns closely with actual deformation patterns, supporting its explanatory value.

Related papers

• CoRe: Joint Optimization with Contrastive Learning for Medical Image Registration [2.6926304126225893]
  We propose a novel framework that integrates contrastive learning directly into the registration model.<n>By jointly optimizing the contrastive and registration objectives, we ensure that the learned representations are not only informative but also suitable for the registration task.
  arXiv  Detail & Related papers  (2026-03-24T20:08:34Z)
• Multimodal Diffeomorphic Registration with Neural ODEs and Structural Descriptors [0.0]
  multimodal diffeomorphic registration method using Neural Ordinary Differential Equations (Neural ODEs)<n>Nonrigid registration algorithms exhibit tradeoffs between their accuracy, the computational complexity of their deformation model, and its proper regularization.<n>We propose an instance-specific framework that is not subject to high scan requirements for training and does not suffer degradation at inference time on modalities unseen during training.
  arXiv  Detail & Related papers  (2025-12-27T19:38:37Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [59.062085785106234]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration.<n>We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables.<n>Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• Latent State Models of Training Dynamics [51.88132043461152]
  We train models with different random seeds and compute a variety of metrics throughout training. We then fit a hidden Markov model (HMM) over the resulting sequences of metrics. We use the HMM representation to study phase transitions and identify latent "detour" states that slow down convergence.
  arXiv  Detail & Related papers  (2023-08-18T13:20:08Z)
• Unsupervised Image Registration Towards Enhancing Performance and Explainability in Cardiac And Brain Image Analysis [3.5718941645696485]
  Inter- and intra-modality affine and non-rigid image registration is an essential medical image analysis process in clinical imaging. We present an un-supervised deep learning registration methodology which can accurately model affine and non-rigid trans-formations. Our methodology performs bi-directional cross-modality image synthesis to learn modality-invariant latent rep-resentations.
  arXiv  Detail & Related papers  (2022-03-07T12:54:33Z)
• DiffuseMorph: Unsupervised Deformable Image Registration Along Continuous Trajectory Using Diffusion Models [31.826844124173984]
  We present a novel approach of diffusion model-based probabilistic image registration, called DiffuseMorph. Our model learns the score function of the deformation between moving and fixed images. Our method can provide flexible and accurate deformation with a capability of topology preservation.
  arXiv  Detail & Related papers  (2021-12-09T08:41:23Z)
• Domain Shift in Computer Vision models for MRI data analysis: An Overview [64.69150970967524]
  Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yet only a few applications are now in clinical use. Poor transferability of themodels to data from different sources or acquisition domains is one of the reasons for that.
  arXiv  Detail & Related papers  (2020-10-14T16:34:21Z)
• An Auto-Context Deformable Registration Network for Infant Brain MRI [54.57017031561516]
  We propose an infant-dedicated deep registration network that uses the auto-context strategy to gradually refine the deformation fields. Our method estimates the deformation fields by invoking a single network multiple times for iterative deformation refinement. Experimental results in comparison with state-of-the-art registration methods indicate that our method achieves higher accuracy while at the same time preserves the smoothness of the deformation fields.
  arXiv  Detail & Related papers  (2020-05-19T06:00:13Z)
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond [62.730497582218284]
  We develop a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data.
  arXiv  Detail & Related papers  (2020-04-30T03:23:45Z)
• Deform-GAN:An Unsupervised Learning Model for Deformable Registration [4.030402376540977]
  In this paper, a non-rigid registration method is proposed for 3D medical images leveraging unsupervised learning. The proposed gradient loss is robust across sequences and modals for large deformation. Neither ground-truth nor manual labeling is required during training.
  arXiv  Detail & Related papers  (2020-02-26T12:20:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.