基于KAN的隐式神经表示的可变形医学图像配准
Deformable Medical Image Registration with KAN-based Implicit Neural Representations
AI总结：
提出基于KAN的INR框架KAN-IDIR与RandKAN-IDIR，用于无需数据集级训练的逐对优化可变形医学图像配准，在多模态医学图像上实现高准确性、低开销与稳定性，适用于临床研究。
摘要：
可变形图像配准（DIR）是医学图像分析的核心，支持纵向研究和多模态融合的空间对齐。基于学习的方法如CNN和Transformer可实现快速推理，但通常需要大量训练数据集，且在特定解剖结构或模态上的表现常逊于经典迭代方法。隐式神经表示（INR）通过将变形场建模为连续的坐标-位移映射，提供了一种数据高效的替代方案，然而其逐对优化的特性要求运行时效率和初始化鲁棒性良好。我们提出KAN-IDIR和RandKAN-IDIR，这是首个基于Kolmogorov-Arnold网络（KAN）的INR框架，用于逐对优化、与分辨率无关的DIR，旨在无需数据集级训练即可提高种子稳定性和资源效率。KAN使用可学习的激活函数，非常适合连续的、具有物理结构的变形场。RandKAN-IDIR通过随机基采样进一步降低成本，用更少的基函数保持配准质量。我们在肺CT、脑MRI和心脏MRI数据集上，与逐对INR方法、基于数据集训练的深度模型及经典基线进行了评估。KAN-IDIR和RandKAN-IDIR在基于INR的方法中实现了最高的准确性，且计算开销低，在随机初始化下具有出色的稳定性。RandKAN-IDIR的表现略优于自适应基选择变体，同时避免了其额外的训练时间复杂度，这使得该方法适用于可重复的临床研究使用。源代码可在this https URL获取。
英文摘要：
Deformable image registration (DIR) is central to medical image analysis, supporting spatial alignment for longitudinal studies and multi-modal fusion. Learning-based methods such as CNNs and transformers provide rapid inference but often require large training datasets and can underperform classical iterative methods for specific anatomies or modalities. Implicit neural representations (INRs) offer a data-efficient alternative by modeling deformation fields as continuous coordinate-to-displacement mappings, yet their per-pair optimization makes runtime efficiency and robustness to initialization essential. We introduce KAN-IDIR and RandKAN-IDIR, the first Kolmogorov--Arnold network (KAN)-based INR framework for pairwise-optimized, resolution-independent DIR, designed to improve seed stability and resource efficiency without dataset-level training. KANs use learnable activation functions that are well suited to continuous, physically structured deformation fields. RandKAN-IDIR further reduces cost through randomized basis sampling, preserving registration quality with fewer basis functions. We evaluate the methods on lung CT, brain MRI, and cardiac MRI datasets against pairwise INR approaches, dataset-trained deep models, and classical baselines. KAN-IDIR and RandKAN-IDIR achieve the highest accuracy among INR-based methods, with low computational overhead and superior stability across random initializations. RandKAN-IDIR slightly outperforms adaptive basis selection variants while avoiding their additional training-time complexity. This makes the approach practical for reproducible clinical research use. Source code is available at https://github.com/anac0der/KAN-IDIR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
