Department of CT/MRI, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China.
Department of Neurology, Jinjiang Municipal Hospital, Quanzhou 362000, China.
Comput Methods Programs Biomed. 2023 Apr;231:107437. doi: 10.1016/j.cmpb.2023.107437. Epub 2023 Feb 21.
Automated segmentation techniques for cardiac magnetic resonance imaging (MRI) are beneficial for evaluating cardiac functional parameters in clinical diagnosis. However, due to the characteristics of unclear image boundaries and anisotropic resolution anisotropy produced by cardiac magnetic resonance imaging technology, most of the existing methods still have the problems of intra-class uncertainty and inter-class uncertainty. However, due to the irregularity of the anatomical shape of the heart and the inhomogeneity of tissue density, the boundaries of its anatomical structures become uncertain and discontinuous. Therefore, fast and accurate segmentation of cardiac tissue remains a challenging problem in medical image processing.
We collected cardiac MRI data from 195 patients as training set and 35patients from different medical centers as external validation set. Our research proposed a U-net network architecture with residual connections and a self-attentive mechanism (Residual Self-Attention U-net, RSU-Net). The network relies on the classic U-net network, adopts the U-shaped symmetric architecture of the encoding and decoding mode, improves the convolution module in the network, introduces skip connections, and improves the network's capacity for feature extraction. Then for solving locality defects of ordinary convolutional networks. To achieve a global receptive field, a self-attention mechanism is introduced at the bottom of the model. The loss function employs a combination of Cross Entropy Loss and Dice Loss to jointly guide network training, resulting in more stable network training.
In our study, we employ the Hausdorff distance (HD) and the Dice similarity coefficient (DSC) as metrics for assessing segmentation outcomes. Comparsion was made with the segmentation frameworks of other papers, and the comparison results prove that our RSU-Net network performs better and can make accurate segmentation of the heart. New ideas for scientific research.
Our proposed RSU-Net network combines the advantages of residual connections and self-attention. This paper uses the residual links to facilitate the training of the network. In this paper, a self-attention mechanism is introduced, and a bottom self-attention block (BSA Block) is used to aggregate global information. Self-attention aggregates global information, and has achieved good segmentation results on the cardiac segmentation dataset. It facilitates the diagnosis of cardiovascular patients in the future.
心脏磁共振成像（MRI）的自动化分割技术有益于在临床诊断中评估心脏功能参数。然而，由于心脏磁共振成像技术产生的图像边界不清晰和各向异性分辨率各向异性的特点，大多数现有的方法仍然存在类内不确定性和类间不确定性的问题。然而，由于心脏解剖形状的不规则性和组织密度的不均匀性，其解剖结构的边界变得不确定和不连续。因此，快速准确地分割心脏组织仍然是医学图像处理中的一个具有挑战性的问题。
我们从 195 名患者收集心脏 MRI 数据作为训练集，从不同医疗中心收集 35 名患者作为外部验证集。我们的研究提出了一种具有残差连接和自注意机制的 U-net 网络架构（Residual Self-Attention U-net，RSU-Net）。该网络依赖于经典的 U-net 网络，采用编码和解码模式的 U 形对称架构，改进网络中的卷积模块，引入跳跃连接，提高网络的特征提取能力。然后，为了解决普通卷积网络的局域性缺陷。为了实现全局感受野，在模型底部引入了自注意机制。损失函数采用交叉熵损失和 Dice 损失的组合来共同指导网络训练，从而使网络训练更加稳定。
在我们的研究中，我们采用 Hausdorff 距离（HD）和 Dice 相似系数（DSC）作为评估分割结果的指标。与其他论文的分割框架进行了比较，比较结果证明我们的 RSU-Net 网络性能更好，可以对心脏进行准确分割。为科学研究提供了新的思路。
我们提出的 RSU-Net 网络结合了残差连接和自注意的优点。本文利用残差链接来促进网络的训练。在本文中，引入了自注意机制，并使用底部自注意块（BSA Block）来聚合全局信息。自注意机制聚合全局信息，在心脏分割数据集上取得了良好的分割效果。有助于未来心血管患者的诊断。
