ID 原文 译文
2003 在多个授权的本地基站(Base Station BS)上建立了一个联盟区块链，用于公开审计和共享交易记录。 A consortium block-chain has been established on the BSs for publicly auditing and sharing of transaction records without depending on the trus-ted third parties.
2004 资源交易记录在加密后上传到 BS。 The resource transaction records are uploaded to the BS after encryption.
2005 在交易记录通过审查和共识过程之后，新区块被存储在 BS 上，并且可以由 MTCG，LTE 用户和连接到联盟区块链的 BS 进行公开访问。 After the transaction records passthe review and consensus process, the new blocks are stored on the BSs that can be accessed publicly by MTCGs, LTE usersand the BSs connected to the consortium blockchain.
2006 为了最大化系统的利益，支持频繁的资源交易，提出了一种基于信用贷款的支付方案，并给出了相应的最优定价策略。 In order to maximize the benefits of the system and support frequent re-source transactions, a credit-based payment scheme and the corresponding optimal pricing strategy are proposed.
2007 为提高胶质母细胞瘤(GBM)多模态磁共振(MR)图像中各肿瘤子区域分割的准确性，提出一种多分类卷积神经网络(CNN)的 GBM 多模态 MR 图像自动分割算法。 To improve the accuracy of segmenting the tumor sub-regions in glioblastoma multiforme (GBM)multi-modal magnetic resonance (MR)images, a GBM multi-modal MR images automatic segmentation algorithm is proposed byusing multi-class convolution neural network (CNN).
2008 首先在 98% 缩尾处理和配准 GBM 多模态 MR 图像后，利用 N4ITK 法校正偏移场; Firstly, after 98% winsorization and registration for the GBM multi-modal MR images, the bias field was corrected by using the N4ITK method.
2009 其次构建一个主要由 4 个卷积层、2 个池化层和 2 个全连接层组成的多分类 CNN 模型，训练后预分割 GBM 多模态 MR 图像，将体素分为 5 类不同的标签; Secondly, a multi-class CNN model mainly con-sisting of four convolutional layers, two pooling layers and two fully connected layers was constructed;the GBM multi-modalMR images were pre-segmented after training, and voxels were classified into five different labels.
2010 最后移除所有小于 200 体素的假阳性区域，中值滤波后获得最终分割结果。 Finally, all false positive regions smaller than 200 voxels were removed, and the final segmentation results were obtained by median filtering.
2011 以 Dice 相似性系数 DSC、阳性预测值 PPV 和平均 Hausdorff 距离 AHD 为评价指标，利用所提出的算法对 F-C-GBM 数据集中整个肿瘤组织进行分割，获得的 DSC、PPV、AHD 分别为 0.889 ± 0.087、0.859 ± 0.127 和1.923。 TheDice similarity coefficient DSC, positive predictive value PPV and average Hausdorff distance AHD were adopted as the e-valuation index, and the DSC, PPV as well as AHD were 0. 889 ± 0. 087, 0. 859 ± 0. 127 and 1. 923 for segmenting the entiretumor tissues in F-C-GBM dataset by the proposed algorithm, respectively.
2012 结果表明，该算法能有效提高 GBM 多模态 MR 图像分割的性能，可望有临床应用前景。 Results indicate that the proposed method can ef-fectively improve the performance in the segmentation of the GBM multi-modal MR images and may be expected to have clinical application prospects.