Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks.
Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks.
复制标题
DOI：
10.3390/diagnostics11091629
复制
发表时间：
2021-09-06
期刊：
影响因子：
--
通讯作者：
Mizukami S
中科院分区：
文献类型：
--
作者：
Gomi T;Sakai R;Hara H;Watanabe Y;Mizukami S
在这项研究中，利用投影数据开发了一种新的混合生成对抗网络（GANs）组合，包括周期一致的GAN， pix2pix和（掩模金字塔网络）MPN (cgpm -金属伪影减少[MAR])，以减少数字断层合成过程中的金属伪影和辐射剂量。将CGpM-MAR算法与不带MAR的传统滤波反投影（FBP）、带MAR的FBP和卷积神经网络MAR算法进行比较。使用假体假体在不同辐射剂量下的伪影指数（AI）和最大变异分析的Gumbel分布对MAR率进行比较。新型CGpM-MAR在人工智能方面产生了足够有效的整体性能。所得到的图像具有良好的效果，与假体所用的金属类型无关（p < 0.05），并且在辐射剂量降低55%时良好地去除了伪影。此外，cppm - mar在模型中最小，在辐射剂量减少55%时变化最大。在人工智能和Gumbel分布分析方面，在辐射剂量降低55%的情况下，与传统的有和没有MAR的重建算法相比，新型CGpM-MAR产生了更好的MAR，并呈现出与参考FBP最相似的特征。CGpM-MAR是一种很有前途的金属伪影和降低辐射剂量的方法。
In this study, a novel combination of hybrid generative adversarial networks (GANs) comprising cycle-consistent GAN, pix2pix, and (mask pyramid network) MPN (CGpM-metal artifact reduction [MAR]), was developed using projection data to reduce metal artifacts and the radiation dose during digital tomosynthesis. The CGpM-MAR algorithm was compared with the conventional filtered back projection (FBP) without MAR, FBP with MAR, and convolutional neural network MAR. The MAR rates were compared using the artifact index (AI) and Gumbel distribution of the largest variation analysis using a prosthesis phantom at various radiation doses. The novel CGpM-MAR yielded an adequately effective overall performance in terms of AI. The resulting images yielded good results independently of the type of metal used in the prosthesis phantom (p < 0.05) and good artifact removal at 55% radiation-dose reduction. Furthermore, the CGpM-MAR represented the minimum in the model with the largest variation at 55% radiation-dose reduction. Regarding the AI and Gumbel distribution analysis, the novel CGpM-MAR yielded superior MAR when compared with the conventional reconstruction algorithms with and without MAR at 55% radiation-dose reduction and presented features most similar to the reference FBP. CGpM-MAR presents a promising method for metal artifact and radiation-dose reduction in clinical practice.
登录
查看更多内容
影响因子：
3.8
作者：
Bal, Matthieu;Spies, Lothar
通讯作者：
Spies, Lothar
DOI：
10.1016/j.compmedimag.2009.01.004
发表时间：
2009-06-01
影响因子：
5.7
作者：
Gomi, Tsutomu;Hirano, Hiroshi;Umeda, Tokuo
通讯作者：
Umeda, Tokuo
影响因子：
10.6
作者：
Liao, Haofu;Lin, Wei-An;Luo, Jiebo
通讯作者：
Luo, Jiebo
影响因子：
1.3
作者：
ROBERTSON, DD;WEISS, PJ;WALKER, PS
通讯作者：
WALKER, PS
影响因子：
19.7
作者：
KALENDER, WA;HEBEL, R;EBERSBERGER, J
通讯作者：
EBERSBERGER, J