Neural Optimization for Image Registration via Joint Modeling of Global Affine and Local Deformation Transformations
- 28 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (02780062) , 1
Abstract
Conventional registration approaches frequently underperform when applied to sparse feature alignment (e.g., retinal vessels and filamentous collagen fibers in second-harmonic generation (SHG) and bright-field (BF) images), as these tasks demand simultaneous handling of global affine registration and local deformation correction. End-to-end learning-based approaches struggle with minimal effective gradients from loss back-propagation of these sparse features, while descriptor matching methods, though helpful, lack fidelity loss and fail to adapt to local deformation. To address these issues, we propose Neural Affine Optimization (NeOn), which implicitly approximates discrete optimization using a few neural network layers, combined with a sampling-regression layer to handle affine transformations. NeOn allows iterative refinement with fidelity loss and provides a flexible transition between a purely affine configuration and a linear weighted blend of affine and deformation fields. NeOn’s performance was validated on four public datasets. In multi-modal SHG-BF microscopy registration, NeOn achieved top rankings on the validation leaderboard for Task 3 of the Learn2Reg Challenge 2024. For retinal image registration, NeOn outperformed existing methods on both mono-modal and multi-modal datasets, reducing target registration error from 6.3 to 2.1 pixels in mono-modal and from 2.6 to 1.8 pixels in multi-modal registration. Furthermore, NeOn demonstrates strong generalization and can be effectively extended to 3D multi-modality image registration scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (62425305)
- National Natural Science Foundation of China (62503161)
- National Natural Science Foundation of China (U22B2050)
- Natural Science Foundation of Hunan Province (2025JJ60389)
- Science and Technology Program of Hunan Province (2025RC3069)
This publication has 62 references indexed in Scilit:
- Coordinate Translator for Learning Deformable Medical Image Registration2022
- Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration2022
- Voxelmorph++2022
- Fast 3D Registration with Accurate Optimisation and Little Learning for Learn2Reg 20212022
- A Deep Discontinuity-Preserving Image Registration Network2021
- Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration2021
- An Unsupervised Learning Approach to Discontinuity-Preserving Image Registration2020
- Closing the Gap Between Deep and Conventional Image Registration Using Probabilistic Dense Displacement Networks2019
- Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration2019
- A longitudinal four‐dimensional computed tomography and cone beam computed tomography dataset for image‐guided radiation therapy research in lung cancerMedical Physics, 2016