Kuo Licheng, Li Feifei, Fu Yabo, Zhang Hao, Cervino Laura A, Moran Jean M, Li Xiang, Li Tianfang
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, USA.
Med Phys. 2025 Jul;52(7):e18000. doi: 10.1002/mp.18000.
BACKGROUND: Kilovoltage cone-beam computed tomography (kV CBCT) is vital for image-guided radiotherapy (IGRT). The new RTI4343iL panel on the Varian TrueBeam LINAC offers higher resolution but requires binning to achieve practical frame rates, leading to projection resolution loss. Existing super-resolution (SR) techniques have been applied to enhance CBCT image quality but primarily operate in the image domain, struggling to restore resolution loss in the projection domain. PURPOSE: This study aimed to evaluate the feasibility of a deep learning (DL) SR model, based on a conditional Generative Adversarial Networks (cGANs) architecture, for enhancing the spatial resolution of CBCT acquired with the new RTI4343iL panel in the projection domain. We hypothesize that projection-domain deblurring will primarily depend on the detector and minimally on patient anatomy, enhancing primary signal resolution without significantly altering scatter distribution. The study quantitatively assessed the impact of SR-enhanced projections on the quality of reconstructed CBCT images. METHODS: A DLSR model was developed to enhance CBCT resolution in the projection domain. For data acquisition, a Varian TrueBeam system equipped with the RTI4343iL panel was used, which features a native high-resolution image size of 2848 × 2144 pixels, but operates in 2 × 8 binning mode (1424 × 268 pixels) during CBCT scans to mitigate data readout speed limitations. Following thorax CBCT protocols, 576 pairs of CBCT projections were acquired at two resolutions using Rando, Longman, and Steeve phantoms. Of these, 460 pairs were allocated for model training, while 116 were reserved for validation. Model testing involved 144 Dynamic Thorax projections and CBCT reconstructions utilizing Catphan 604 phantoms. The DL SR model was built on a cGANs framework with a U-Net generator. Image enhancement was quantitatively evaluated with metrics including peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index measure (SSIM), feature similarity index measure (FSIM), and mean absolute percentage error (MAPE). RESULTS: The DL SR model effectively enhanced image resolution, producing SR projections with greater detail and improved structural clarity. Quantitative analysis showed that the SR-enhanced projections outperformed upscaled low-resolution (LR) projections with higher PSNR (44.4 vs. 43.7, p < 0.001), lower MSE (187,083.7 vs. 205,364.4, p < 0.001), and improved MAPE (7.6% vs. 13.5%, p < 0.001). While SSIM and FSIM values were similar for both methods, the SR-enhanced projections demonstrated a slight advantage, achieving an FSIM of 0.998. Reconstructed CBCT images from SR-enhanced projections exhibited improved spatial resolution as well, increasing from 0.6 lp/mm to 0.9 lp/mm on the Catphan 604 phantom image. Enhanced structural detail and sharper intensity profiles in SR CBCT images further validated the model's potential to restore resolution lost during the acquisition process. CONCLUSION: This study underscores the efficacy of a projection-domain DL SR method for CBCT enhancement. The developed model presents a promising avenue for attaining high-resolution CBCT, potentially benefiting for many clinical applications.
背景：千伏级锥形束计算机断层扫描（kV CBCT）对图像引导放射治疗（IGRT）至关重要。瓦里安TrueBeam直线加速器上的新型RTI4343iL平板提供了更高的分辨率，但需要进行合并以实现实际帧率，这会导致投影分辨率损失。现有的超分辨率（SR）技术已被应用于提高CBCT图像质量，但主要在图像域中运行，难以恢复投影域中的分辨率损失。 目的：本研究旨在评估基于条件生成对抗网络（cGANs）架构的深度学习（DL）SR模型在投影域中提高使用新型RTI4343iL平板采集的CBCT空间分辨率的可行性。我们假设投影域去模糊将主要取决于探测器，而对患者解剖结构的依赖最小，在不显著改变散射分布的情况下提高原始信号分辨率。该研究定量评估了SR增强投影对重建CBCT图像质量的影响。 方法：开发了一种DLSR模型以提高投影域中的CBCT分辨率。对于数据采集，使用配备RTI4343iL平板的瓦里安TrueBeam系统，其原生高分辨率图像尺寸为2848×2144像素，但在CBCT扫描期间以2×8合并模式（1424×268像素）运行，以减轻数据读出速度限制。按照胸部CBCT协议，使用Rando、Longman和Steeve体模以两种分辨率采集了576对CBCT投影。其中，460对用于模型训练，116对留作验证。模型测试涉及144个动态胸部投影和使用Catphan 604体模的CBCT重建。DL SR模型基于带有U-Net生成器的cGANs框架构建。使用包括峰值信噪比（PSNR）、均方误差（MSE）、结构相似性指数测量（SSIM）、特征相似性指数测量（FSIM）和平均绝对百分比误差（MAPE）等指标对图像增强进行定量评估。 结果：DL SR模型有效地提高了图像分辨率，生成了具有更多细节和更高结构清晰度的SR投影。定量分析表明，SR增强投影在PSNR更高（44.4对43.7，p<0.001）、MSE更低（187,083.7对205,364.4，p<0.001）以及MAPE改善（7.6%对13.5%，p<0.001）方面优于放大后的低分辨率（LR）投影。虽然两种方法的SSIM和FSIM值相似，但SR增强投影显示出轻微优势，FSIM达到0.998。从SR增强投影重建的CBCT图像也表现出空间分辨率的提高，在Catphan 604体模图像上从0.6 lp/mm增加到0.9 lp/mm。SR CBCT图像中增强的结构细节和更清晰的强度轮廓进一步验证了该模型恢复采集过程中损失的分辨率的潜力。 结论：本研究强调了投影域DL SR方法用于CBCT增强的有效性。所开发的模型为获得高分辨率CBCT提供了一条有前景的途径，可能使许多临床应用受益。
Comput Methods Programs Biomed. 2023-8
Procedia Comput Sci. 2022
Zotero 插件