Luo Feng, Ma Chaoyu, Shi Juntian, Xu Kunyuan
South China Normal University, Guangzhou, China.
Sun Yat-sen Memorial Hospital, Guangzhou, China.
Neuroradiology. 2025 May 7. doi: 10.1007/s00234-025-03634-w.
Cone-beam computed tomography (CBCT) is instrumental in image-guided radiation therapy (IGRT), providing low radiation exposure while continuously monitoring anatomical structures for accurate dose estimation and treatment. Despite these advantages, CBCT inherently suffers from lower image quality and more frequent artifacts compared to computed tomography (CT), significantly undermining its effectiveness in IGRT. These drawbacks are especially pronounced in the pelvic region, where anatomical variability and dataset asymmetry challenge traditional image translation techniques like diffusion and CycleGAN networks.
To overcome these limitations, we propose CycleDiffSmoothGAN(CDSGAN), an innovative framework that enhances CBCT images by integrating CycleGAN with latent diffusion techniques and high-frequency detail preservation.This approach effectively blends features in the latent space, enabling smoother transitions between CBCT and synthetic CT (sCT) images.
The implementation of CDSGAN has shown superior performance, significantly outperforming existing technologies across crucial imaging metrics such as MAE ( Hu), PSNR ( dB), SSIM ( ), and FID ( ).
The research findings have substantiated the promising potential of CDSGAN in enhancing image quality for clinical applications.
锥形束计算机断层扫描（CBCT）在图像引导放射治疗（IGRT）中发挥着重要作用，它在提供低辐射暴露的同时，持续监测解剖结构以进行准确的剂量估计和治疗。尽管具有这些优势，但与计算机断层扫描（CT）相比，CBCT本质上存在图像质量较低和伪影更频繁的问题，这严重削弱了其在IGRT中的有效性。这些缺点在盆腔区域尤为明显，该区域的解剖结构变异性和数据集不对称性对扩散和CycleGAN网络等传统图像转换技术构成了挑战。
为克服这些限制，我们提出了CycleDiffSmoothGAN（CDSGAN），这是一个创新框架，通过将CycleGAN与潜在扩散技术及高频细节保留相结合来增强CBCT图像。这种方法有效地在潜在空间中融合特征，使CBCT图像与合成CT（sCT）图像之间的过渡更加平滑。
CDSGAN的实施显示出卓越的性能，在诸如平均绝对误差（MAE，Hu）、峰值信噪比（PSNR，dB）、结构相似性指数（SSIM）和弗雷歇因距离（FID）等关键成像指标上显著优于现有技术。
研究结果证实了CDSGAN在提高临床应用图像质量方面具有广阔的潜力。
