发表机构
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Southern University of Science and Technology; Huashan Hospital, Fudan University（中国科学院深圳先进技术研究院; 南方科技大学; 复旦大学附属华山医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出RefineCBCT，一种基于伪标签引导短步扩散的非配对CBCT精化框架，在LUNG和PELVIC TCIA数据集上优于GAN和扩散方法，有效减少伪影并保留解剖结构。
AI 中文摘要
锥束计算机断层扫描（CBCT）广泛应用于图像引导放疗，但散射、束硬化、噪声、截断及其他伪影限制了图像质量和CT值准确性。由于运动、解剖变化和采集不匹配，临床上难以获得配对的CBCT和CT数据。我们提出了RefineCBCT，一种非配对CBCT精化框架，利用伪标签引导和短步扩散来减少伪影，同时保留患者特定解剖结构。RefineCBCT在来自公共LUNG TCIA和PELVIC TCIA数据集的非配对CBCT和计划CT数据上进行了训练和评估，并与代表性的基于GAN和扩散的方法进行了比较。在LUNG TCIA上，它在所有指标上取得了最佳结果，MAE为19.411，RMSE为62.758，PSNR为30.845 dB，SSIM为0.931。在PELVIC TCIA上，它取得了最佳的MAE、PSNR和SSIM，数值分别为14.905、36.671 dB和0.876。精化后的图像显示出更少的条纹和阴影伪影，更清晰的解剖边界，以及改善的软组织均匀性，线轮廓和感兴趣区域分析显示与计划CT更接近的一致性。这些结果表明，RefineCBCT在临床现实非配对训练条件下提供了高效有效的CBCT精化，并可能支持在图像引导放疗工作流程中更可靠地使用CBCT。代码已在GitHub上公开，评估数据集可从癌症影像档案获取。
英文摘要
Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy, but scatter, beam hardening, noise, truncation, and other artifacts limit image quality and CT number accuracy. Paired CBCT and CT data are difficult to obtain clinically because of motion, anatomical changes, and acquisition mismatch. We present RefineCBCT, an unpaired CBCT refinement framework that uses pseudo-label guidance and short-step diffusion to reduce artifacts while preserving patient-specific anatomy. RefineCBCT was trained and evaluated on unpaired CBCT and planning CT data from public LUNG TCIA and PELVIC TCIA datasets and compared with representative GAN and diffusion based methods. On LUNG TCIA, it achieved the best results across all metrics, with MAE 19.411, RMSE 62.758, PSNR 30.845 dB, and SSIM 0.931. On PELVIC TCIA, it achieved the best MAE, PSNR, and SSIM, with values of 14.905, 36.671 dB, and 0.876. The refined images showed fewer streaking and shading artifacts, clearer anatomical boundaries, and improved soft tissue uniformity, with line profile and ROI analyses showing closer agreement with planning CT. These results suggest that RefineCBCT provides efficient and effective CBCT refinement under clinically realistic unpaired training conditions and may support more reliable CBCT use in image-guided radiotherapy workflows. Code is publicly available on GitHub, and the evaluated datasets are available from The Cancer Imaging Archive.
