Zhao Xuzhi, Du Yi, Peng Yahui
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China.
Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, China.
J Imaging Inform Med. 2025 Jan 23. doi: 10.1007/s10278-025-01390-0.
While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections. The sinogram restoration model was modified from the 2D U-Net by incorporating dynamic convolutional layers and residual learning techniques. The DLMPS approach was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Sparse-view projection datasets with 1/4 and 1/8 of the original sampling rate were simulated, and the corresponding full-view projection datasets were restored via the DLMPS approach. Tomographic images were reconstructed using the Feldkamp-Davis-Kress algorithm. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated in both the projection and image domains to evaluate the performance of the DLMPS approach. The DLMPS approach was compared with 11 state-of-the-art (SOTA) models, including CNN and Transformer architectures. For 1/4 sparse-view reconstruction task, the proposed DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0271, 45.93 dB, 0.9817, and 0.9587 in the projection domain, and 0.000885, 37.63 dB, 0.9074, and 0.9885 in the image domain, respectively. For 1/8 sparse-view reconstruction task, the DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0304, 44.85 dB, 0.9785, and 0.9524 in the projection domain, and 0.001057, 36.05 dB, 0.8786, and 0.9774 in the image domain, respectively. The DLMPS approach outperformed all the 11 SOTA models in both the projection and image domains for 1/4 and 1/8 sparse-view reconstruction tasks. The proposed DLMPS approach effectively improves the quality of sparse-view CBCT images in IGRT by accurately synthesizing missing projections, exhibiting potential in substantially reducing imaging dose to patients with minimal loss of image quality.
虽然在图像引导放射治疗（IGRT）中，锥束计算机断层扫描（CBCT）所产生的辐射危害可通过稀疏视图采样来降低，但图像质量不可避免地会下降。我们提出一种基于深度学习的多视图投影合成（DLMPS）方法，以提高稀疏视图低剂量CBCT图像的质量。在所提出的DLMPS方法中，首先对稀疏视图投影应用线性插值，并将投影重新排列成正弦图；这些正弦图用正弦图恢复模型进行处理，然后再重新排列回投影。通过合并动态卷积层和残差学习技术，对2D U-Net模型进行修改，得到正弦图恢复模型。DLMPS方法分别在来自163、30和30名真实患者的CBCT数据上进行训练、验证和测试。模拟了采样率为原始采样率1/4和1/8的稀疏视图投影数据集，并通过DLMPS方法恢复相应的全视图投影数据集。使用Feldkamp-Davis-Kress算法重建断层图像。在投影域和图像域中计算包括均方根误差（RMSE）、峰值信噪比（PSNR）、结构相似性（SSIM）和特征相似性（FSIM）在内的定量指标，以评估DLMPS方法的性能。将DLMPS方法与11种最新的（SOTA）模型进行比较，包括CNN和Transformer架构。对于1/4稀疏视图重建任务，所提出的DLMPS方法在投影域中的平均RMSE、PSNR、SSIM和FSIM值分别为0.0271、45.93 dB、0.9817和0.9587，在图像域中分别为0.000885、37.63 dB、0.9074和0.9885。对于1/8稀疏视图重建任务，DLMPS方法在投影域中的平均RMSE、PSNR、SSIM和FSIM值分别为0.0304、44.85 dB、0.9785和0.9524，在图像域中分别为0.001057、36.05 dB、0.8786和0.9774。在1/4和1/8稀疏视图重建任务的投影域和图像域中，DLMPS方法均优于所有11种SOTA模型。所提出的DLMPS方法通过准确合成缺失的投影，有效提高了IGRT中稀疏视图CBCT图像的质量，在大幅降低患者成像剂量且图像质量损失最小方面展现出潜力。
