ty -jour au -tang，chao au -li，jie au -wang，linyuan au -li -li，ziheng au -jiang -jiang，lingyun au -cai -cai，ailong au -zhang -Zhang，wenkun au -liang -liang-YAN，BIN PY -2019 DA -2019/12/07 TI-基于周期符合的生成对抗网络，带有先验图像信息SP -8639825 VL -2019 AB- 2019 AB- X射线应用程序的广泛应用临床诊断中的断层扫描（CT）导致公众对对患者的过度辐射剂量的关注增加。但是，减少辐射剂量将不可避免地引起服务器噪声并影响放射科医生的判断和信心。因此，必须开发出进行性低剂量CT（LDCT）图像重建方法以提高图像质量。在过去的两年中，基于深度学习的方法在LDCT图像的降噪方面表现出了令人印象深刻的性能。大多数现有的深度学习方法通​​常都需要配对的训练数据集，LDCT图像对应于正常剂量CT（NDCT）图像一对一，但是对配对良好的数据集的获取需要进行多次扫描，从而增加辐射剂量。因此，不容易获得良好的数据集。为了解决此问题，本文提出了一个基于周期生成对抗网络（Cyclegan）的未配对的LDCT图像Denoising网络，其中不需要一对一的培训数据集。 In this method, cyclic loss, an important trick in unpaired image-to-image translation, promises to map the distribution from LDCT to NDCT by using unpaired training data. Furthermore, to guarantee the accurate correspondence of the image content between the output and NDCT, the prior information obtained from the result preprocessed using the LDCT image is integrated into the network to supervise the generation of content. Given the map of distribution through the cyclic loss and the supervision of content through the prior image loss, our proposed method can not only reduce the image noise but also retain critical information. Real-data experiments were carried out to test the performance of the proposed method. The peak signal-to-noise ratio (PSNR) improves by more than 3 dB, and the structural similarity (SSIM) increases when compared with the original CycleGAN without prior information. The real LDCT data experiment demonstrates the superiority of the proposed method according to both visual inspection and quantitative evaluation. SN - 1748-670X UR - https://doi.org/10.1155/2019/8639825 DO - 10.1155/2019/8639825 JF - Computational and Mathematical Methods in Medicine PB - Hindawi KW - ER -