The Advanced Imaging and Informatics for Radiation Therapy (AIRT) Laboratory, 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.
Phys Med Biol. 2024 Jun 26;69(13):135008. doi: 10.1088/1361-6560/ad580d.
Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy. Reconstructing CBCTs from limited-angle acquisitions (LA-CBCT) is highly desired for improved imaging efficiency, dose reduction, and better mechanical clearance. LA-CBCT reconstruction, however, suffers from severe under-sampling artifacts, making it a highly ill-posed inverse problem. Diffusion models can generate data/images by reversing a data-noising process through learned data distributions; and can be incorporated as a denoiser/regularizer in LA-CBCT reconstruction. In this study, we developed a diffusion model-based framework, prior frequency-guided diffusion model (PFGDM), for robust and structure-preserving LA-CBCT reconstruction.PFGDM uses a conditioned diffusion model as a regularizer for LA-CBCT reconstruction, and the condition is based on high-frequency information extracted from patient-specific prior CT scans which provides a strong anatomical prior for LA-CBCT reconstruction. Specifically, we developed two variants of PFGDM (PFGDM-A and PFGDM-B) with different conditioning schemes. PFGDM-A applies the high-frequency CT information condition until a pre-optimized iteration step, and drops it afterwards to enable both similar and differing CT/CBCT anatomies to be reconstructed. PFGDM-B, on the other hand, continuously applies the prior CT information condition in every reconstruction step, while with a decaying mechanism, to gradually phase out the reconstruction guidance from the prior CT scans. The two variants of PFGDM were tested and compared with current available LA-CBCT reconstruction solutions, via metrics including peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).PFGDM outperformed all traditional and diffusion model-based methods. The mean(s.d.) PSNR/SSIM were 27.97(3.10)/0.949(0.027), 26.63(2.79)/0.937(0.029), and 23.81(2.25)/0.896(0.036) for PFGDM-A, and 28.20(1.28)/0.954(0.011), 26.68(1.04)/0.941(0.014), and 23.72(1.19)/0.894(0.034) for PFGDM-B, based on 120°, 90°, and 30° orthogonal-view scan angles respectively. In contrast, the PSNR/SSIM was 19.61(2.47)/0.807(0.048) for 30° for DiffusionMBIR, a diffusion-based method without prior CT conditioning.. PFGDM reconstructs high-quality LA-CBCTs under very-limited gantry angles, allowing faster and more flexible CBCT scans with dose reductions.
锥形束计算机断层扫描（CBCT）广泛应用于图像引导放疗。从有限角度采集（LA-CBCT）重建 CBCT 以提高成像效率、降低剂量和更好的机械间隙是非常需要的。然而，LA-CBCT 重建受到严重的欠采样伪影的影响，使其成为一个高度不适定的逆问题。扩散模型可以通过学习的数据分布来反转数据噪声过程来生成数据/图像；并且可以作为 LA-CBCT 重建的去噪器/正则化器合并。在这项研究中，我们开发了一种基于扩散模型的框架，即基于先验频率引导的扩散模型（PFGDM），用于稳健和结构保留的 LA-CBCT 重建。PFGDM 使用条件扩散模型作为 LA-CBCT 重建的正则化器，条件基于从患者特定的先验 CT 扫描中提取的高频信息，为 LA-CBCT 重建提供了强大的解剖先验。具体来说，我们开发了两种变体的 PFGDM（PFGDM-A 和 PFGDM-B），它们具有不同的条件方案。PFGDM-A 在达到预优化的迭代步骤之前应用高频 CT 信息条件，之后将其丢弃，以便重建相似和不同的 CT/CBCT 解剖结构。另一方面，PFGDM-B 在每个重建步骤中都连续应用先验 CT 信息条件，同时具有衰减机制，以逐渐从先验 CT 扫描中消除重建指导。通过包括峰值信噪比（PSNR）和结构相似性指数度量（SSIM）在内的指标，对 PFGDM 的两种变体进行了测试和与当前可用的 LA-CBCT 重建解决方案进行了比较。PFGDM 优于所有传统和基于扩散模型的方法。PFGDM-A 的平均（标准差）PSNR/SSIM 分别为 27.97(3.10)/0.949(0.027)、26.63(2.79)/0.937(0.029)和 23.81(2.25)/0.896(0.036)，PFGDM-B 的平均（标准差）PSNR/SSIM 分别为 28.20(1.28)/0.954(0.011)、26.68(1.04)/0.941(0.014)和 23.72(1.19)/0.894(0.034)，分别基于 120°、90°和 30°正交视图扫描角度。相比之下，在没有先验 CT 条件的情况下，扩散 MBIR（一种基于扩散的方法）的 PSNR/SSIM 为 30°时的 19.61(2.47)/0.807(0.048)。PFGDM 在非常有限的旋转角度下重建高质量的 LA-CBCT，允许更快和更灵活的 CBCT 扫描，同时降低剂量。
