无需呼吸门控，实现连续时间动态CT重建
X$^{2}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction
- 用动态辐射高斯点阵建模器官运动，避免分相导致的错位
- 在无外部设备条件下，通过可微优化学习患者呼吸周期
- 相比传统方法提升9.93 dB PSNR，适合临床动态成像需求
四维计算机断层扫描（4D CT）对捕捉动态解剖变化至关重要，但传统基于相位分箱的工作流程存在固有限制。现有方法将时间分辨率离散化为固定相位，依赖呼吸门控设备，导致运动错位且临床实用性受限。本文提出X²-Gaussian，一种新框架，通过融合动态辐射高斯点阵与自监督呼吸运动学习，实现连续时间4D-CT重建。该方法采用时空编码器-解码器架构，预测随时间变化的高斯形变，消除相位离散化。为摆脱对外部门控设备的依赖，引入生理驱动的周期一致性损失，通过可微优化直接从投影数据中学习患者特异性呼吸周期。大量实验表明，该方法达到顶尖性能，相较传统方法提升9.93 dB PSNR，较先前高斯点阵技术提高2.25 dB。通过统一连续运动建模与无硬件周期学习，X²-Gaussian推动高保真动态临床成像发展。代码公开于：https://x2-gaussian.github.io/。
原文摘要 · Abstract (English)
Four-dimensional computed tomography (4D CT) reconstruction is crucial for capturing dynamic anatomical changes but faces inherent limitations from conventional phase-binning workflows. Current methods discretize temporal resolution into fixed phases with respiratory gating devices, introducing motion misalignment and restricting clinical practicality. In this paper, We propose X$^2$-Gaussian, a novel framework that enables continuous-time 4D-CT reconstruction by integrating dynamic radiative Gaussian splatting with self-supervised respiratory motion learning. Our approach models anatomical dynamics through a spatiotemporal encoder-decoder architecture that predicts time-varying Gaussian deformations, eliminating phase discretization. To remove dependency on external gating devices, we introduce a physiology-driven periodic consistency loss that learns patient-specific breathing cycles directly from projections via differentiable optimization. Extensive experiments demonstrate state-of-the-art performance, achieving a 9.93 dB PSNR gain over traditional methods and 2.25 dB improvement against prior Gaussian splatting techniques. By unifying continuous motion modeling with hardware-free period learning, X$^2$-Gaussian advances high-fidelity 4D CT reconstruction for dynamic clinical imaging. Code is publicly available at: https://x2-gaussian.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。