DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called DrivenMorph to improve medical image alignment, especially for 3D brain scans. Their approach uses ideas from traditional Demons algorithms combined with modern deep learning, allowing for clear and explainable control of how images are deformed. By focusing on the differences between images in a special feature space, their method guides the alignment process more accurately and smoothly. Tests showed it performed better than current top methods, and the results help explain how the alignment forces relate to actual shape changes.
Medical Image RegistrationDeep LearningDemons AlgorithmVariational Image RegistrationAttention MechanismsLatent Feature SpaceDeformation3D Brain MRIExplainabilityDriving Force
Authors
Mingke Li, Jianping Zhang, Jinqiu Deng
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.