ID 原文 译文
41216 相比于现有的各类高速并行数据传输解决方案，该系统具备可软件定义的数据接入能力，也能支持更加灵活的随路时钟动态范围。 Compared with the existing high speed parallel data transmission system, the one presented in this paper has software-defined access capability and supports more flexible dynamic range for the different sampling clock.
41217 同时，通过设计精简合理的帧结构，推导数据位宽与随路时钟之间的约束关系，有效提高了系统传输带宽。 What is more, through the design of simplified and reasonable frame structure, and the constraint relation between the data bit width and the sampling clock is deduced, the system can improve the effective transmission bandwidth obviously.
41218 测试结果表明，该系统工作稳定可靠，实时传输效果好，时钟恢复精度可达100fs，扩展了串并转换与并串转换技术的应用领域。 The test results show that this system can work stably and reliably with an excellent real-time transmission effect, and have the high precision of clock recovery.Meanwhile the system extends the application field of serializer and deserializer technology, and it provides a high reference value for other transmission systems.
41219 针对图像噪声以及血管、支气管等因素引起的肺分割困难的问题，提出了一种基于逻辑校准的多分类残差网络分割算法。 In order to extract lung precisely, aiming at difficulty in segmentation of lung caused by interfering factors such as image noise, blood vessels and bronchus, an algorithm based on logit adjustment in multi-class residual network was proposed.
41220 该算法将图像区域划分为肺、背景及边界三类，通过扩大不同类型间的差异来提升分割准确率。 The algorithm divided the image area into three categories:lung, background and boundary, which improves the segmentation accuracy by expanding the difference between different types of images.
41221 算法先将图像分割为固定尺寸区域，然后利用残差网络提取纹理特征进行分类训练与测试，实现粗分割。 Firstly, the image was divided into regions with fixed size, then, a residual network was then trained to extract the texture features for classification and tested to achieve coarse segmentation.
41222 最后对边界区域阈值处理实现细分割。 Finally, refining segmentation was conducted on regions which were marked as boundary based on threshold method.
41223 利用公开数据集对该算法进行了测试， The segmentation performance of the proposed model was tested and verified by using apublic dataset.
41224 实验结果表明，此分割算法在召回率、精确率以及交并比等方面均优于当下前沿的分割网络之一的U-Net，分别达到99.79%，98.13%和97.83%， The recall rate, precision and intersection over union of the algorithm were obtained as 99.79%, 98.13% and 97.83%, respectively, and the overall segmentation performance was higher than that of U-Net, one of the most cutting-edge segmentation networks.
41225 可为后续的肺部疾病临床诊断提供参考依据。 According to the experimental results, the proposed algorithm provides a reference basis for subsequent clinical diagnosis of lung diseases.