基于残差编解码-生成对抗网络的正弦图修复的稀疏角度锥束CT图像重建  

Sinogram inpainting for sparse-view cone-beam computed tomography image reconstruction based on residual encoder-decoder generative adversarial network

作　　者：靳鑫 刘仰川[2] 朱叶晨 张子健[3] 高欣 JIN Xin;LIU Yangchuan;ZHU Yechen;ZHANG Zijian;GAO Xin(Division of Life Sciences and Medicine,School of Biomedical Engineering(Suzhou),University of Science and Technology of China,Suzhou Jiangsu 215009,China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou Jiangsu 215163,China;Department of Oncology,Xiangya Hospital,Central South University,Changsha Hunan 410008,China)

机构地区：[1]中国科学技术大学生物医学工程学院(苏州)生命科学与医学部,江苏苏州215009 [2]中国科学院苏州生物医学工程技术研究所,江苏苏州215163 [3]中南大学湘雅医院肿瘤科,长沙410008

出　　处：《计算机应用》2023年第6期1950-1957,共8页journal of Computer Applications

基　　金：国家自然科学基金资助项目(81871439);山东省重点研发计划项目(2021SFGC0104);江苏省重点研发计划项目(BE2021663);苏州市科技计划项目(SJC20211014)。

摘　　要：稀疏投影可有效缩短锥束CT(CBCT)扫描剂量和扫描时间,但会导致重建图像中出现大量条状伪影。正弦图修复可以生成缺失角度的投影数据,并提高重建图像质量。基于这些,提出了一种用于稀疏角度CBCT重建的正弦图修复的残差编解码-生成对抗网络(RED-GAN)。该网络利用残差编解码结构(RED)模块替换Pix2pixGAN(Pix2pixGenerative Adversarial Network)中的U-Net生成器,并利用基于PatchGAN(Patch Generative Adversarial Network)的条件判别器鉴别修复后的正弦图和真实正弦图,从而进一步提升网络性能。利用真实CBCT投影数据进行网络训练后,分别在1/2、1/3、1/4稀疏采样条件下测试所提网络,并把RED-GAN与线性插值法、残差编解码-卷积神经网络(RED-CNN)和Pix2pixGAN对比。实验结果表明,RED-GAN的正弦图修复结果在3种条件下均优于对比方法,并在1/4稀疏采样条件下所提网络的优势最为明显。在正弦图域中,RED-GAN的均方根误差(RMSE)下降了7.2%,峰值信噪比(PSNR)上升了1.5%,结构相似性(SSIM)上升了1.4%;在重建图像域中,RMSE下降了5.4%,PSNR上升了1.6%,SSIM上升了1.0%。可见,RED-GAN适用于高质量的稀疏角度CBCT重建,在快速低剂量CBCT扫描领域具有潜在的应用价值。Sparse-view projection can reduce the scan does and scan time of Cone-Beam Computed Tomography(CBCT)effectively but brings a lot of streak artifacts to the reconstructed images.Sinogram inpainting can generate projection data for missing angles and improve the quality of reconstructed images.Based on the above,a Residual Encoder-Decoder Generative Adversarial Network(RED-GAN)was proposed for sinogram inpainting to reconstruct sparse-view CBCT images.In this network,the U-Net generator in Pix2pixGAN(Pix2pix Generative Adversarial Network)was replaced with the Residual Encoder-Decoder(RED)module.In addition,the conditional discriminator based on PatchGAN(Patch Generative Adversarial Network)was used to distinguish between the repaired sinograms from the real sinograms,thereby further improving the network performance.After the network training using real CBCT projection data,the proposed network was tested under 1/2,1/3 and 1/4 sparse-view sampling conditions,and compared with linear interpolation method,Residual Encoder-Decoder Convolutional Neural Network(RED-CNN)and Pix2pixGAN.Experimental results indicate that the sinogram inpainting results of RED-GAN are better than those of the comparison methods under all the three conditions.Under the 1/4 sparse-view sampling condition,the proposed network has the most obvious advantages.In the sinogram domain,the proposed network has the Root Mean Square Error(RMSE)decreased by 7.2%,Peak Signal-to-Noise Ratio(PSNR)increased by 1.5%and Structural Similarity(SSIM)increased by 1.4%;in the reconstructed image domain,the proposed network has the RMSE decreased by 5.4%,PSNR increased by 1.6%and SSIM increased by 1.0%.It can be seen that RED-GAN is suitable for high-quality CBCT reconstruction and has potential application value in the field of fast low-dose CBCT scanning.

关 键 词：锥束CT 稀疏角度 正弦图修复 生成对抗网络 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]