arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.01575eess.IVcs.CV
收藏

HC$^3$L-Diff:用于CBCT到CT合成的带高频增强的混合条件潜在扩散模型

HC$^3$L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis

National University of Singapore(新加坡国立大学);Central South University(中南大学);National Cancer Centre Singapore(新加坡国家癌症中心);Duke-NUS Medical School(杜克-新加坡国立大学医学院);Nanyang Technological University(南洋理工大学);The Institute for Digital Medicine (WisDM), National University of Singapore(新加坡国立大学数字医学研究所(WisDM));The N.1 Institute for Health (N.1), National University of Singapore(新加坡国立大学N.1健康研究所);Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学杨潞龄医学院);The Bia-Echo Asia Centre for Reproductive Longevity and Equality (ACRLE), National University of Singapore(新加坡国立大学Bia-Echo亚洲生殖长寿与平等中心);College of Design and Engineering, National University of Singapore(新加坡国立大学设计与工程学院)

Shi Yin, Hongqi Tan, Li Ming Chong, Haofeng Liu, Hui Liu, Kang Hao Lee, Jeffrey Kit Loong Tuan, Dean Ho, Yueming Jin

AI总结:

针对CBCT因伪影噪声无法用于精准放疗剂量计算的问题,提出带高频增强的混合条件潜在扩散模型HC³L-Diff,通过UFE压缩、HFE提取高频信息作为条件、快速采样实现高效高质量CBCT转CT,剂量评估表现优异,适配临床自适应放疗。

摘要:

研究背景:锥形束计算机断层扫描(CBCT)在图像引导放射治疗中发挥着关键作用,但其存在的伪影和噪声使其无法用于精确的剂量计算。人工智能方法在提升CBCT质量以生成合成CT(sCT)图像方面已展现出潜力,但现有方法要么生成的图像质量欠佳,要么耗时过长,无法满足临床实践标准。方法与材料:我们提出了一种新型混合条件潜在扩散模型,用于高效且精准的CBCT到CT合成,命名为HC$^3$L-Diff。我们采用统一特征编码器(Unified Feature Encoder, UFE)将图像压缩到低维潜在空间,以此优化计算效率。除了使用CBCT图像外,我们提出将其高频知识作为混合条件整合进来,引导扩散模型生成保留结构细节的sCT图像;该高频信息由我们设计的高频提取器(High-Frequency Extractor, HFE)捕获。在推理阶段,我们使用去噪扩散隐式模型以实现快速采样。我们构建了一个全新的内部前列腺数据集,包含配对的CBCT和CT图像,用于验证我们方法的有效性。结果:大量实验结果表明,我们的方法在sCT质量和生成效率方面均优于当前最优方法。此外,我们的医学物理学家进行了剂量学评估,以验证我们的方法在实际剂量计算中的优势,在2%/2mm标准下达到了93.8%的优异伽马通过率,优于其他方法。结论:所提出的HC$^3$L-Diff可高效实现高质量的CBCT到CT合成,每位患者仅需2分多钟。其在剂量计算中的优异表现,为提升实际临床中的自适应放射治疗效果展现出巨大潜力。

英文摘要:

Background: Cone-beam computed tomography (CBCT) plays a crucial role in image-guided radiotherapy, but artifacts and noise make them unsuitable for accurate dose calculation. Artificial intelligence methods have shown promise in enhancing CBCT quality to produce synthetic CT (sCT) images. However, existing methods either produce images of suboptimal quality or incur excessive time costs, failing to satisfy clinical practice standards. Methods and materials: We propose a novel hybrid conditional latent diffusion model for efficient and accurate CBCT-to-CT synthesis, named HC$^3$L-Diff. We employ the Unified Feature Encoder (UFE) to compress images into a low-dimensional latent space, thereby optimizing computational efficiency. Beyond the use of CBCT images, we propose integrating its high-frequency knowledge as a hybrid condition to guide the diffusion model in generating sCT images with preserved structural details. This high-frequency information is captured using our designed High-Frequency Extractor (HFE). During inference, we utilize denoising diffusion implicit model to facilitate rapid sampling. We construct a new in-house prostate dataset with paired CBCT and CT to validate the effectiveness of our method. Result: Extensive experimental results demonstrate that our approach outperforms state-of-the-art methods in terms of sCT quality and generation efficiency. Moreover, our medical physicist conducts the dosimetric evaluations to validate the benefit of our method in practical dose calculation, achieving a remarkable 93.8% gamma passing rate with a 2%/2mm criterion, superior to other methods. Conclusion: The proposed HC$^3$L-Diff can efficiently achieve high-quality CBCT-to-CT synthesis in only over 2 mins per patient. Its promising performance in dose calculation shows great potential for enhancing real-world adaptive radiotherapy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑