Unsupervised Deformable Image Registration with Local-Global Attention and Image Decomposition

• URL: http://arxiv.org/abs/2601.14337v1
• Date: Tue, 20 Jan 2026 13:19:13 GMT
• Title: Unsupervised Deformable Image Registration with Local-Global Attention and Image Decomposition
• Authors: Zhengyong Huang, Xingwen Sun, Xuting Chang, Ning Jiang, Yao Wang, Jianfei Sun, Hongbin Han, Yao Sui,
• Abstract summary: Deformable image registration is a critical technology in medical image analysis, with broad applications in clinical practice such as disease diagnosis, multi-modal fusion, and surgical navigation.<n>Recent advances in deep learning have introduced attention-based mechanisms that improve feature alignment, yet accurately registering regions with high anatomical variability remains challenging.<n>In this study, we proposed a novel unsupervised deformable image registration framework, LGANet++, which employs a novel local-global attention mechanism integrated with a unique technique for feature interaction and fusion to enhance registration accuracy, robustness, and generalizability.
• Score: 9.035666469536054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deformable image registration is a critical technology in medical image analysis, with broad applications in clinical practice such as disease diagnosis, multi-modal fusion, and surgical navigation. Traditional methods often rely on iterative optimization, which is computationally intensive and lacks generalizability. Recent advances in deep learning have introduced attention-based mechanisms that improve feature alignment, yet accurately registering regions with high anatomical variability remains challenging. In this study, we proposed a novel unsupervised deformable image registration framework, LGANet++, which employs a novel local-global attention mechanism integrated with a unique technique for feature interaction and fusion to enhance registration accuracy, robustness, and generalizability. We evaluated our approach using five publicly available datasets, representing three distinct registration scenarios: cross-patient, cross-time, and cross-modal CT-MR registration. The results demonstrated that our approach consistently outperforms several state-of-the-art registration methods, improving registration accuracy by 1.39% in cross-patient registration, 0.71% in cross-time registration, and 6.12% in cross-modal CT-MR registration tasks. These results underscore the potential of LGANet++ to support clinical workflows requiring reliable and efficient image registration. The source code is available at https://github.com/huangzyong/LGANet-Registration.

Related papers

• Attention-Driven Framework for Non-Rigid Medical Image Registration [15.540035635369504]
  We propose a novel Attention-Driven Framework for Non-Rigid Medical Image Registration (AD-RegNet)<n>Our approach combines a 3D UNet backbone with bidirectional cross-attention, which establishes correspondences between moving and fixed images at multiple scales.<n>The proposed method maintains a favorable balance between registration accuracy and computational efficiency, making it suitable for clinical applications.
  arXiv  Detail & Related papers  (2026-02-06T09:23:37Z)
• SAMIR, an efficient registration framework via robust feature learning from SAM [40.09295562721889]
  This paper introduces SAMIR, an efficient medical image registration framework.<n>SAM is pretrained on large-scale natural image datasets and can learn robust, general-purpose visual representations.<n>We show that SAMIR significantly outperforms state-of-the-art methods on benchmark datasets for both intra-subject cardiac image registration and inter-subject abdomen CT image registration.
  arXiv  Detail & Related papers  (2025-09-17T01:56:35Z)
• Implicit Deformable Medical Image Registration with Learnable Kernels [0.6749750044497731]
  Deformable medical image registration is an essential task in computer-assisted interventions.<n>Recent AI methods can outperform traditional techniques in accuracy and speed.<n>We introduce a novel implicit registration framework that can predict accurate and reliable deformations.
  arXiv  Detail & Related papers  (2025-06-02T18:27:11Z)
• IMPACT: A Generic Semantic Loss for Multimodal Medical Image Registration [0.46904601975060667]
  IMPACT (Image Metric with Pretrained model-Agnostic Comparison for Transmodality registration) is a novel similarity metric designed for robust multimodal image registration.<n>It defines a semantic similarity measure based on the comparison of deep features extracted from large-scale pretrained segmentation models.<n>It was evaluated on five challenging 3D registration tasks involving thoracic CT/CBCT and pelvic MR/CT datasets.
  arXiv  Detail & Related papers  (2025-03-31T14:08:21Z)
• Efficient MedSAMs: Segment Anything in Medical Images on Laptop [69.28565867103542]
  We organized the first international competition dedicated to promptable medical image segmentation.<n>The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline.<n>The best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption.
  arXiv  Detail & Related papers  (2024-12-20T17:33:35Z)
• Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR images [74.99415008543276]
  Most deep learning-based registration methods assume that the deformation fields are smooth and continuous everywhere in the image domain. We propose a novel discontinuity-preserving image registration method to tackle this challenge, which ensures globally discontinuous and locally smooth deformation fields. A co-attention block is proposed in the segmentation component of the network to learn the structural correlations in the input images. We evaluate our method on the task of intra-subject-temporal image registration using large-scale cinematic cardiac magnetic resonance image sequences.
  arXiv  Detail & Related papers  (2022-11-24T23:45:01Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• A Deep Discontinuity-Preserving Image Registration Network [73.03885837923599]
  Most deep learning-based registration methods assume that the desired deformation fields are globally smooth and continuous. We propose a weakly-supervised Deep Discontinuity-preserving Image Registration network (DDIR) to obtain better registration performance and realistic deformation fields. We demonstrate that our method achieves significant improvements in registration accuracy and predicts more realistic deformations, in registration experiments on cardiac magnetic resonance (MR) images.
  arXiv  Detail & Related papers  (2021-07-09T13:35:59Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• F3RNet: Full-Resolution Residual Registration Network for Deformable Image Registration [21.99118499516863]
  Deformable image registration (DIR) is essential for many image-guided therapies. We propose a novel unsupervised registration network, namely the Full-Resolution Residual Registration Network (F3RNet) One stream takes advantage of the full-resolution information that facilitates accurate voxel-level registration. The other stream learns the deep multi-scale residual representations to obtain robust recognition.
  arXiv  Detail & Related papers  (2020-09-15T15:05:54Z)
• A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint [20.905285486843006]
  We propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registrations. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed. Our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU.
  arXiv  Detail & Related papers  (2020-08-05T01:16:45Z)

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.