当前位置: X-MOL 学术Int. J. Pattern Recognit. Artif. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Blood Vessel Segmentation Based on the 3D Residual U-Net
International Journal of Pattern Recognition and Artificial Intelligence ( IF 0.9 ) Pub Date : 2021-08-14 , DOI: 10.1142/s021800142157007x
Mulin Xin 1 , Jing Wen 1 , Yi Wang 1 , Wei Yu 1 , Bin Fang 1 , Jun Hu 2 , Yongmei Xu 2 , Chunhong Linghu 2
Affiliation  

In this paper, we propose blood vessel segmentation based on the 3D residual U-Net method. First, we integrate the residual block structure into the 3D U-Net. By exploring the influence of adding residual blocks at different positions in the 3D U-Net, we establish a novel and effective 3D residual U-Net. In addition, to address the challenges of pixel imbalance, vessel boundary segmentation, and small vessel segmentation, we develop a new weighted Dice loss function with a better effect than the weighted cross-entropy loss function. When training the model, we adopted a two-stage method from coarse-to-fine. In the fine stage, a local segmentation method of 3D sliding window is added. In the model testing phase, we used the 3D fixed-point method. Furthermore, we employ the 3D morphological closed operation to smooth the surfaces of vessels and volume analysis to remove noise blocks. To verify the accuracy and stability of our method, we compare our method with FCN, 3D DenseNet, and 3D U-Net. The experimental results indicate that our method has higher accuracy and better stability than the other studied methods and that the average Dice coefficients for hepatic veins and portal veins reach 71.7% and 76.5% in the coarse stage and 72.5% and 77.2% in the fine stage, respectively. In order to verify the robustness of the model, we conducted the same comparative experiment on the brain vessel datasets, and the average Dice coefficient reached 87.2%.

中文翻译:

基于 3D Residual U-Net 的血管分割

在本文中,我们提出了基于 3D 残差 U-Net 方法的血管分割。首先,我们将残差块结构集成到 3D U-Net 中。通过探索在 3D U-Net 中不同位置添加残差块的影响,我们建立了一种新颖有效的 3D 残差 U-Net。此外,为了解决像素不平衡、血管边界分割和小血管分割的挑战,我们开发了一种新的加权 Dice 损失函数,其效果优于加权交叉熵损失函数。在训练模型时,我们采用了从粗到细的两阶段方法。在精细阶段,增加了一种3D滑动窗口的局部分割方法。在模型测试阶段,我们使用了 3D 定点法。此外,我们采用 3D 形态学闭合运算来平滑血管表面和体积分析以去除噪声块。为了验证我们方法的准确性和稳定性,我们将我们的方法与 FCN、3D DenseNet 和 3D U-Net 进行了比较。实验结果表明,我们的方法比其他研究方法具有更高的准确性和更好的稳定性,肝静脉和门静脉的平均 Dice 系数在粗略阶段达到 71.7% 和 76.5%,在精细阶段达到 72.5% 和 77.2% , 分别。为了验证模型的稳健性,我们在脑血管数据集上进行了相同的对比实验,平均 Dice 系数达到 87.2%。实验结果表明,我们的方法比其他研究方法具有更高的准确性和更好的稳定性,肝静脉和门静脉的平均 Dice 系数在粗略阶段达到 71.7% 和 76.5%,在精细阶段达到 72.5% 和 77.2% , 分别。为了验证模型的稳健性,我们在脑血管数据集上进行了相同的对比实验,平均 Dice 系数达到 87.2%。实验结果表明,我们的方法比其他研究方法具有更高的准确性和更好的稳定性,肝静脉和门静脉的平均 Dice 系数在粗略阶段达到 71.7% 和 76.5%,在精细阶段达到 72.5% 和 77.2% , 分别。为了验证模型的稳健性,我们在脑血管数据集上进行了相同的对比实验,平均 Dice 系数达到 87.2%。
更新日期:2021-08-14
down
wechat
bug