Intra-fraction motion in radiotherapy is commonly modeled using deformable image registration (DIR). However, existing methods often struggle to balance speed and accuracy, limiting their applicability in clinical scenarios. This study introduces a novel approach that harnesses Neural Graphics Primitives (NGP) to optimize the displacement vector field (DVF). Our method leverages learned primitives, processed as splats, and interpolates within space using a shallow neural network. Uniquely, it enables self-supervised optimization at an ultra-fast speed, negating the need for pre-training on extensive datasets and allowing seamless adaptation to new cases. We validated this approach on the 4D-CT lung dataset DIR-lab, achieving a target registration error (TRE) of 1.15\pm1.15 mm within a remarkable time of 1.77 seconds. Notably, our method also addresses the sliding boundary problem, a common challenge in conventional DIR methods.

翻译：放疗中的分次内运动通常采用可变形图像配准（DIR）进行建模。然而，现有方法常难以兼顾速度与精度，限制了其临床适用性。本研究提出一种创新方法，利用神经图形基元（NGP）优化位移矢量场（DVF）。该方法采用经处理的基元（以splats形式处理），并通过浅层神经网络在空间中进行插值。独特之处在于，它能够实现超快速的自监督优化，无需在大规模数据集上预训练，且可无缝适应新病例。我们在4D-CT肺部数据集DIR-lab上验证了该方法，在仅1.77秒的显著时间内实现了1.15±1.15毫米的目标配准误差（TRE）。值得注意的是，该方法还解决了传统DIR方法中常见的滑动边界问题。