Deep Learning‑Based Approach for the Automatic Quantification of Epicardial Adipose Tissue from Non‑Contrast CT
Deep Learning‑Based Approach for the Automatic Quantification of Epicardial Adipose Tissue from Non‑Contrast CT
复制标题
基于深度学习的非造影 CT 心外膜脂肪组织自动定量方法
DOI：
10.1007/s12559-022-10036-0
复制
发表时间：
2022
影响因子：
5.4
通讯作者：
Xu Zhang
中科院分区：
文献类型：
--
作者：
Junda Qu;Yuting Chang;Liwe Sun;Yutang Li;Qian Si;Min-Fu Yang;Chunlin Li;Xu Zhang
心外膜脂肪组织（EAT）与动脉和心肌相邻。 EAT 量的增加可能会导致不良心血管事件。因此，对 EAT 进行量化是必要的。本文的目的是采用一种非常有用的算法来进行 EAT 分割和量化。首先，我们使用简单的卷积神经网络来选择 EAT 切片，这显着减少了过度分割。然后，我们采用多尺度残差注意力 Unet (MRA-Unet) 来实现基于所选切片的 EAT 分割。最后，我们计算分段体积来量化 EAT。我们使用 33/103 名患者来测试该模型。 EAT 分割的平均 Dice 得分为 0.883。对于 EAT 量化，Pearson 相关系数和一致性相关系数分别达到 0.973 和 0.971。结果表明，我们的算法与专家有很强的一致性和一致性。我们的方法进行了高效的量化，并且与专家手动标记的体积具有很强的一致性和一致性。该算法可用作辅助 EAT 临床量化的工具。通过结合不同的测量来预测不良心血管和心脏病事件，它有可能在未来应用于临床。
Epicardial adipose tissue (EAT) is contiguous with arteries and myocardium. An increase in the volume of EAT may lead to adverse cardiovascular events. Therefore, quantification of EAT is necessary. The purpose of this paper is to employ a more than helpful algorithm for EAT segmentation and quantification. First, we used a simple convolutional neural network to select EAT slices, which significantly reduced oversegmentation. Then, we employed multiscale residual attention Unet (MRA-Unet) to achieve EAT segmentation based on the selected slices. Finally, we calculated the segmented volume to quantify EAT. We used 33/103 patients to test the model. The average Dice score for EAT segmentation was 0.883. For EAT quantification, the Pearson and concordance correlation coefficients reached 0.973 and 0.971, respectively. The results showed that our algorithm had strong agreement and consistency with expert. Our method performed efficient quantification and had strong consistency and agreement with the volume manually marked by experts. This algorithm can be used as a tool to assist in the clinical quantification of EAT. By combining different measurements to predict adverse cardiovascular and heart disease events, it has the potential to be applied for clinical use in the future.