As an important pre-processing step in clinical applications, automatic and accurate 3D cardiovascular image segmentation has attracted more and more attention. However, cardiovascular structures are often with high diversity, blood pool and myocardium shapes are also with large variability, and ambiguous cardiac borders make the segmentation task very challenging. In this paper, a novel deep neural network to segment the blood pool and myocardium from three dimensional cardiovascular images is introduced by fully exploiting the global context and complementary information encoded in different feature extraction layers, referred to as GCEFG-R 2 Net briefly. In order to semantically locate the two kinds of regions in a global manner, we design a global context pooling module which can effectively learn context information in a global manner from the deep features extracted from the last two deep layers. Instead of directly using or combining different levels of deep features, we develop an interactive feature aggregation strategy to enhance different levels of deep features by embedding a series of interactive feature aggregation modules. By using the enhanced features, a residual feature refining branch is designed for refining the side outputs in a top-down stream with the guidance of global context features. Finally, the refined side outputs of different layers and the enhanced deep features are combined to generate the final segmentation result by using a feature fusion module. Extensive experiments on two challenge datasets are conducted to demonstrate that the proposed GCEFG-R 2 Net can obtain appealing segmentation results for the blood pool and myocardium and performs better than other state-of-the-art methods.

中文翻译：

---

 目录


作为临床应用中重要的预处理步骤，自动、准确的3D心血管图像分割越来越受到人们的关注。然而，心血管结构往往具有高度多样性，血池和心肌形状也具有很大的变异性，模糊的心脏边界使得分割任务非常具有挑战性。本文提出了一种新颖的深度神经网络，通过充分利用全局上下文和不同特征提取层中编码的互补信息，从三维心血管图像中分割血池和心肌，简称GCEFG-R 2 Net。为了以全局方式在语义上定位这两种区域，我们设计了一个全局上下文池化模块，该模块可以从最后两个深层提取的深层特征中有效地以全局方式学习上下文信息。我们不是直接使用或组合不同级别的深层特征，而是开发一种交互式特征聚合策略，通过嵌入一系列交互式特征聚合模块来增强不同级别的深层特征。通过使用增强的特征，设计了残余特征细化分支，用于在全局上下文特征的指导下细化自上而下流中的侧输出。最后，使用特征融合模块将不同层的细化侧输出和增强的深度特征结合起来，生成最终的分割结果。对两个挑战数据集进行了广泛的实验，以证明所提出的 GCEFG-R 2 Net 可以获得有吸引力的血池和心肌分割结果，并且比其他最先进的方法表现得更好。