cIDIR: Conditioned Implicit Neural Representation for Regularized Deformable Image Registration
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913945854410752 |
|---|---|
| author | Hadramy, Sidaty El Cherkaoui, Oumeymah Cattin, Philippe C. |
| author_facet | Hadramy, Sidaty El Cherkaoui, Oumeymah Cattin, Philippe C. |
| contents | Regularization is essential in deformable image registration (DIR) to ensure that the estimated Deformation Vector Field (DVF) remains smooth, physically plausible, and anatomically consistent. However, fine-tuning regularization parameters in learning-based DIR frameworks is computationally expensive, often requiring multiple training iterations. To address this, we propose cIDI, a novel DIR framework based on Implicit Neural Representations (INRs) that conditions the registration process on regularization hyperparameters. Unlike conventional methods that require retraining for each regularization hyperparameter setting, cIDIR is trained over a prior distribution of these hyperparameters, then optimized over the regularization hyperparameters by using the segmentations masks as an observation. Additionally, cIDIR models a continuous and differentiable DVF, enabling seamless integration of advanced regularization techniques via automatic differentiation. Evaluated on the DIR-LAB dataset, $\operatorname{cIDIR}$ achieves high accuracy and robustness across the dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | cIDIR: Conditioned Implicit Neural Representation for Regularized Deformable Image Registration Hadramy, Sidaty El Cherkaoui, Oumeymah Cattin, Philippe C. Computer Vision and Pattern Recognition Machine Learning Regularization is essential in deformable image registration (DIR) to ensure that the estimated Deformation Vector Field (DVF) remains smooth, physically plausible, and anatomically consistent. However, fine-tuning regularization parameters in learning-based DIR frameworks is computationally expensive, often requiring multiple training iterations. To address this, we propose cIDI, a novel DIR framework based on Implicit Neural Representations (INRs) that conditions the registration process on regularization hyperparameters. Unlike conventional methods that require retraining for each regularization hyperparameter setting, cIDIR is trained over a prior distribution of these hyperparameters, then optimized over the regularization hyperparameters by using the segmentations masks as an observation. Additionally, cIDIR models a continuous and differentiable DVF, enabling seamless integration of advanced regularization techniques via automatic differentiation. Evaluated on the DIR-LAB dataset, $\operatorname{cIDIR}$ achieves high accuracy and robustness across the dataset. |
| title | cIDIR: Conditioned Implicit Neural Representation for Regularized Deformable Image Registration |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.12953 |