Learning KAN-based Implicit Neural Representations for Deformable Image Registration

Nikita Drozdov, Marat Zinovev, Dmitry V Sorokin

Keywords: medical image registration, implicit neural representations, Kolmogorov-Arnold networks

TL;DR: RandKAN-IDIR is the first model to incorporate Kolmogorov-Arnold Networks (KANs) into implicit neural representation-based deformable image registration. It improves registration accuracy and seed-dependent stability with minimal computational costs.

Abstract:

Deformable image registration (DIR) is a cornerstone of medical image analysis, enabling spatial alignment for tasks like comparative studies and multi-modal fusion. While learning-based methods (e.g., CNNs, transformers) offer fast inference, they often require large training datasets and struggle to match the precision of classical iterative approaches on some organ types and imaging modalities. Implicit neural representations (INRs) have emerged as a promising alternative, parameterizing deformations as continuous mappings from coordinates to displacement vectors.
However, this comes at the cost of requiring pairwise optimization, making computational efficiency and seed-dependent learning stability critical factors for these methods.
In this work, we propose KAN-IDIR and RandKAN-IDIR, the first integration of Kolmogorov-Arnold Networks (KANs) into deformable image registration with implicit neural representations (INRs). The learnable activation functions of KANs and their inherent suitability for approximating physical systems make them ideal for modeling deformation fields. Our proposed randomized basis sampling strategy reduces the required number of basis functions in KAN while maintaining registration quality, thereby significantly lowering computational costs. We evaluated our approach on three diverse datasets (lung CT, brain MRI, cardiac MRI) and compared it with competing pairwise learning-based approaches, dataset-trained deep learning models, and classical registration approaches. KAN-IDIR and RandKAN-IDIR achieved the highest accuracy among INR-based methods across all evaluated modalities and anatomies, with minimal computational overhead and superior learning stability across multiple random seeds. Additionally, we discovered that our RandKAN-IDIR model with randomized basis sampling slightly outperforms the model with learnable basis function indices, while eliminating its additional training-time complexity. Source code is available in the supplementary material.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 14113