Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis.
Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis.
复制标题
循环一致生成对抗网络：在超低剂量CT评估肺结核中对辐射剂量降低和图像质量改善的作用
DOI：
10.3348/kjr.2020.0988
复制
发表时间：
2021-06
影响因子：
4.8
通讯作者：
Lambin P
中科院分区：
文献类型：
--
作者：
Yan C;Lin J;Li H;Xu J;Zhang T;Chen H;Woodruff HC;Wu G;Zhang S;Xu Y;Lambin P
探讨基于循环一致生成对抗网络（CycleGAN）的深度学习方法重建的胸部超低剂量CT（ULDCT）图像质量在肺结核评估中的应用。
2019年6月至2019年11月，前瞻性纳入103例肺结核患者（平均年龄40.8±13.6岁；男性61例，女性42例），先进行标准剂量CT检查（120 kVp，自动曝光控制），随后立即进行ULDCT检查（80 kVp，10 mAs）。将两次连续扫描的图像用于训练CycleGAN框架以进行图像到图像的转换。将CycleGAN算法的去噪效果与混合迭代重建和基于模型的迭代重建进行比较。分别采用重复测量方差分析和Wilcoxon符号秩检验来比较客观测量值和主观图像质量评分。
使用优化的CycleGAN去噪模型，以ULDCT图像作为输入，峰值信噪比和结构相似性指数分别提高了2.0 dB和0.21。CycleGAN生成的去噪ULDCT图像通常能为解剖结构和病理表现的最佳可视化提供满意的图像质量，其图像噪声水平（平均值±标准差[SD]，19.5±3.0亨氏单位[HU]）低于混合迭代重建（66.3±10.5 HU，p < 0.001），且与基于模型的迭代重建噪声水平相似（19.6±2.6 HU，p > 0.908）。CycleGAN生成的图像对肺部病变显示出最高的对比噪声比，其次是基于模型的迭代重建和混合迭代重建。ULDCT的平均有效辐射剂量为0.12 mSv，与标准剂量CT相比平均降低93.9%。
优化的CycleGAN技术可从胸部ULDCT合成诊断可接受的图像用于肺结核评估。
To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.
登录
查看更多内容
影响因子：
6.7
作者：
Finck, Tom;Li, Hongwei;Wiestler, Benedikt
通讯作者：
Wiestler, Benedikt
影响因子：
19.7
作者：
Chen, Kevin T.;Gong, Enhao;Zaharchuk, Greg
通讯作者：
Zaharchuk, Greg
影响因子：
19.7
作者：
Pontana, Francois;Billard, Anne-Sophie;Remy-Jardin, Martine
通讯作者：
Remy-Jardin, Martine
影响因子：
6.7
作者：
Yamada, Yoshitake;Jinzaki, Masahiro;Kuribayashi, Sachio
通讯作者：
Kuribayashi, Sachio
影响因子：
2.6
作者：
Padole, Atul;Digumarthy, Subba;Kalra, Mannudeep K.
通讯作者：
Kalra, Mannudeep K.