Deformable image registration (DIR) is a core problem in medical image analysis; but, unlike labeling decision problems such as classification and segmentation, registration is a problem class that involves stringent physical constraints. Although deep learning methods have made faster registration possible, the resulting models are often difficult to interpret compared to hand-crafted methods with explicit objectives and interpretable physical meaning.
arXiv:2603. 17415v2 Announce Type: replace-cross Abstract: Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference.
By Ivor J. A. Simpson, Neill D. F. Campbell
ReliMorph is a novel 3D deformable registration framework that integrates correspondence reliability with spatial expert routing and residual velocity gating. By using local correlation distributions to assess match ambiguity, the method guides expert fusion and velocity updates during coarse‑to‑fine refinement, with inverse‑inconsistency feedback refining decisions at finer levels. Experiments show that ReliMorph consistently improves anatomical overlap over competing methods in both unimodal and multimodal registration tasks.
By Chenyu Guo, Wenjie Dai, Yiqian Chang, Zhiyuan Zhang, Yunfan Wei, Shuhan Qi
UniReg is a conditional unified model for medical image registration that adapts deformation field estimation based on anatomical priors, registration type constraints, and instance-specific features. It combines the precision of task‑specific learning with the generalization of traditional optimization, enabling effective alignment across diverse CT and MR scenarios within a single framework. Experiments show UniReg outperforms state‑of‑the‑art learning‑based methods in accuracy while providing strong cross‑scenario generalization and reducing training cost and model redundancy.
By Zi Li, Jianpeng Zhang, Tai Ma, Tony C. W. Mok, Yan-Jie Zhou, Zeli Chen, Xianghua Ye, Le Lu, Cheng Chen, Dakai Jin
The paper introduces Recursive Uncertainty-Gated Image Registration (RUGI), an iterative refinement method that updates deformation fields predicted by learning-based registration models using a gating map. Two gating strategies are explored: an uncertainty-based approach and an image residual error approach, both concentrating updates on difficult regions. Experiments on cardiac MRI and echocardiography datasets show that RUGI consistently improves registration accuracy, with the error-gated variant reducing MSE by 27‑37% on pretrained models and lowering ejection fraction estimation errors.
By Clara Rodrigo Gonz\'alez, Oscar Bates, Fu Siong Ng, Meng-Xing Tang
arXiv:2609.08627v1 Announce Type: cross
Abstract: In proton therapy, plans are typically optimized on a single planning CT, making robustness evaluation essential under anatomical changes. However, c...
By Tomas Guija-Valiente, Blanca Rodriguez-Gonzalez, Norberto Malpica