论文标题
关节左心房分割和基于DNN的疤痕定量，并具有空间编码和塑造注意力
Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention
论文作者
论文摘要
我们提出了一个端到端的深神经网络（DNN），该网络可以同时分割左心（LA）腔并量化LA疤痕。该框架通过基于距离变换图引入空间编码（SE）损耗来包含目标的连续空间信息。与常规的基于二进制标签的损失相比，所提出的SE损失可以减少所得分割中的嘈杂斑块，这对于基于深度学习的方法通常可以看出。为了充分利用LA和LA Scars之间固有的空间关系，我们通过明确的表面投影进一步提出了形状注意力（SA）机制，以构建端到端可识别的模型。具体而言，SA方案嵌入了两任任务网络中，以执行关节分割和疤痕定量。此外，提出的方法可以在发现诸如疤痕之类的小且离散的目标时可以减轻严重的级别不平衡问题。我们评估了来自MICCAI2018 LA Challenge的60个LGE MRI数据的拟议框架。对于LA分割，与3D基本U-NET相比，使用二进制跨透镜损失相比，提出的方法将平均Hausdorff距离从36.4 mm降低到20.0 mm。对于疤痕定量，将该方法与文献中报道的结果或算法进行了比较，并表现出更好的性能。
We propose an end-to-end deep neural network (DNN) which can simultaneously segment the left atrial (LA) cavity and quantify LA scars. The framework incorporates the continuous spatial information of the target by introducing a spatially encoded (SE) loss based on the distance transform map. Compared to conventional binary label based loss, the proposed SE loss can reduce noisy patches in the resulting segmentation, which is commonly seen for deep learning-based methods. To fully utilize the inherent spatial relationship between LA and LA scars, we further propose a shape attention (SA) mechanism through an explicit surface projection to build an end-to-end-trainable model. Specifically, the SA scheme is embedded into a two-task network to perform the joint LA segmentation and scar quantification. Moreover, the proposed method can alleviate the severe class-imbalance problem when detecting small and discrete targets like scars. We evaluated the proposed framework on 60 LGE MRI data from the MICCAI2018 LA challenge. For LA segmentation, the proposed method reduced the mean Hausdorff distance from 36.4 mm to 20.0 mm compared to the 3D basic U-Net using the binary cross-entropy loss. For scar quantification, the method was compared with the results or algorithms reported in the literature and demonstrated better performance.
