cIDIR: Conditioned Implicit Neural Representation for Regularized Deformable Image Registration
This addresses a bottleneck in medical imaging for researchers and practitioners by reducing training iterations, though it is incremental as it builds on existing INR methods.
The paper tackles the problem of computationally expensive fine-tuning of regularization parameters in deformable image registration by proposing cIDIR, a framework based on Implicit Neural Representations that conditions on hyperparameters and uses segmentation masks for optimization, achieving high accuracy and robustness on the DIR-LAB dataset.
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.