The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, United States of America.
Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, TX, 77030, United States of America.
Phys Med Biol. 2024 May 23;69(11):115030. doi: 10.1088/1361-6560/ad46dc.
. Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few x-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g. breathing).. We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired x-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular x-ray projections. Specifically, PMF-STINR uses spatial implicit neural representations to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion of the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning.. PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (∼ 0.1 s) resolution and sub-millimeter accuracy.. PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.
动态锥形束计算机断层扫描（CBCT）可以捕获高空间分辨率、时变的图像，用于运动监测、患者定位和放射治疗的自适应计划。然而，动态 CBCT 重建是一个极其不适定的时空逆问题，因为动态序列中的每个 CBCT 体积仅通过一个或几个 X 射线投影捕获，这是由于旋转架旋转速度慢和解剖运动快（例如呼吸）。我们开发了一种基于机器学习的技术，即无先验模型的时空隐式神经表示（PMF-STINR），用于从顺序采集的 X 射线投影中重建动态 CBCT。PMF-STINR 采用联合图像重建和配准方法来解决欠采样挑战，能够从奇异 X 射线投影重建动态 CBCT。具体来说，PMF-STINR 使用空间隐式神经表示来重建参考 CBCT 体积，并应用时间 INR 来表示参考 CBCT 的扫描内动态运动，从而生成动态 CBCT。PMF-STINR 将时间 INR 与基于学习的 B 样条运动模型相结合，以在重建过程中捕获时变的可变形运动。与以前的方法相比，PMF-STINR 的空间 INR、时间 INR 和 B 样条模型都是在重建过程中实时学习的，一次学习完成，无需使用任何患者特定的先验知识或运动分类/分组。PMF-STINR 通过数字体模模拟、物理体模测量以及具有各种成像协议（半扇区/全扇区、全采样/稀疏采样、不同能量和 mAs 设置等）的多机构患者数据集进行了评估。结果表明，基于单次学习的 PMF-STINR 可以准确、稳健地重建动态 CBCT，并以高时间（约 0.1s）分辨率和亚毫米精度捕捉高度不规则的运动。PMF-STINR 可以从传统的 3D CBCT 扫描重建动态 CBCT，并解决扫描内运动，而无需使用任何先验解剖/运动模型或运动分类/分组。它可以为运动管理提供有前途的工具，提供比传统 4D-CBCT 更丰富的运动信息。
