摘要
目的:使用深度学习算法通过学习肺部CT域图像特征,将锥形束CT(CBCT)合成高质量伪CT(sCT)图像。方法:本研究提出一种基于感知损失的循环生成式对抗网络模型(CycleGAN)和迭代配准的sCT生成算法,首先,结合感知损失和循环一致性损失来训练CycleGAN模型生成高质量的sCT图像,然后,利用Elastix配准工具对所生成的sCT图像和计划CT(pCT)图像进行配准,并用来迭代CycleGAN生成器模型。结果:在获取到的70例肺部肿瘤患者的pCT与CBCT数据上进行实验,从定量指标上看,利用本算法生成的sCT与pCT对比的结构相似度指标比CBCT与pCT对比的提升了11.9%,由0.825上升到0.923,均方绝对误差由110.97 HU降至78.62 HU,峰值信噪比由32.21 dB上升到34.74 dB,互信息由1.187上升到1.418。可视化评估中可见该算法大幅度消除了CBCT切片的散射伪影,突显骨质结构同时也修复了软组织结构。通过与当下流行的U-CycleGAN,R-CycleGAN和CUT模型对比,说明了本算法的有效性。结论:本文算法生成sCT图像能够有效减小CBCT与pCT间的剂量误差与结构误差,使其应用于精准的剂量计算,辅助医生的临床放疗诊断成为可能。
Objective To synthesize high-quality synthetic CT(sCT)images from cone beam CT(CBCT)by learning lung CT domain image features with a deep learning algorithm.Methods A sCT generation algorithm which employs perceptual lossbased cyclic generative adversarial network model(CycleGAN)and iterative registration was presented.CycleGAN model was trained to generate high-quality sCT images by combining perceptual loss and cycle consistency loss;and Elastix was used to register the generated sCT image and the planned CT(pCT)image,and iterate CycleGAN generator model.Results Experiments were conducted on the obtained pCT and CBCT data of 70 patients with lung tumors.From a quantitative perspective,the SSIM between sCT generated by the proposed algorithm and pCT was improved by 11.9%as compared with that between CBCT and pCT,increasing from 0.825 to 0.923;additionally,RMSE dropped from 110.97 HU to 78.62 HU,PSNR increased from 32.21 dB to 34.74 dB,and mutual information increased from 1.187 to 1.418.The visual evaluation revealed that the proposed algorithm greatly eliminated the scattering artifacts of CBCT slices,highlighted the bone structure,and repaired the soft tissue structure.The comparisons with U-CycleGAN,R-CycleGAN and CUT models confirmed the effectiveness of the proposed algorithm.Conclusion Using the proposed algorithm for sCT images generation can effectively reduce the dose error and structural error between CBCT and pCT,making it possible to apply the proposed algorithm to accurate dose calculations and assist doctors in clinical diagnosis.
作者
杨涛
黄淼
刘琮
胡志华
陶莉莉
张淑平
YANG Tao;HUANG Miao;LIU Cong;HU Zhihua;TAO Lili;ZHANG Shuping(School of Intelligent Manufacturing and Control Engineering,Shanghai Polytechnic University,Shanghai 201209,China;School of Computer and Information Engineering,Shanghai Polytechnic University,Shanghai 201209,China;School of Internet of Things Engineering,Shanghai Business School,Shanghai 201400,China)
出处
《中国医学物理学杂志》
2025年第1期59-66,共8页
Chinese Journal of Medical Physics
基金
上海市自然科学基金(20ZR1440300)。
