Unsupervised Deformable Image Registration with Local-Global Attention and Image Decomposition
This work addresses the problem of reliable and efficient image registration for medical professionals in clinical applications like disease diagnosis and surgical navigation, representing an incremental improvement over existing deep learning methods.
The paper tackled the challenge of accurately registering medical images with high anatomical variability by proposing LGANet++, an unsupervised deformable image registration framework, which improved registration accuracy by 1.39% in cross-patient, 0.71% in cross-time, and 6.12% in cross-modal CT-MR tasks compared to state-of-the-art methods.
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.