Multi-Views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
Multi-Views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
复制标题
用于心脏 MR 图像左心室容积估计的多视图融合 CNN
DOI：
10.1109/tbme.2017.2762762
复制
发表时间：
2018-09-01
影响因子：
4.6
通讯作者：
Zhang, Henggui
中科院分区：
文献类型：
--
作者：
Luo, Gongning;Dong, Suyu;Zhang, Henggui
目的：左心室容积测定是心脏病诊断的重要手段。本文的目的是解决一个直接的LV容量预测任务。方法：本文提出了一种基于端到端深度卷积神经网络的直接体积预测方法。从数据预处理、网络结构和多视图融合策略等方面研究了端到端左心室容积预测方法。本文的主要贡献在于以下几个方面。首先，我们提出了一种新的心脏磁共振（CMR）数据预处理方法。其次，我们提出了一种新的网络结构，用于端到端LV体积估计。第三，我们探讨了不同切片的代表能力，并提出了一种融合策略，以提高预测精度。结果如下：评估结果表明，该方法优于其他国家的最先进的LV体积估计方法的开放访问的基准数据集。由预测体积导出的临床指标与实际值吻合良好（EDV：R-2 = 0.974，RMSE = 9.6ml; ESV：R-2 = 0.976，RMSE = 7.1ml; EF：R-2 = 0.828，RMSE = 4.71%）。结论：实验结果证明，该方法可以用于左心室容积预测任务。重要性：该方法不仅在大规模CMR数据的心脏疾病筛查中具有应用潜力，而且可以扩展到其他医学图像研究领域。
Objective: Left ventricular (LV) volume estimation is a critical procedure for cardiac disease diagnosis. The objective of this paper is to address a direct LV volume prediction task. Methods: In this paper, we propose a direct volume prediction method based on the end-to- end deep convolutional neural networks. We study the end-to-end LV volume prediction method in items of the data preprocessing, network structure, and multiview fusion strategy. The main contributions of this paper are the following aspects. First, we propose a new data preprocessing method on cardiac magnetic resonance (CMR). Second, we propose a new network structure for end-to-end LV volume estimation. Third, we explore the representational capacity of different slices and propose a fusion strategy to improve the prediction accuracy. Results: The evaluation results show that the proposed method outperforms other state-of-the-art LV volume estimation methods on the open accessible benchmark datasets. The clinical indexes derived from the predicted volumes agree well with the ground truth (EDV: R-2 = 0.974, RMSE = 9.6 ml; ESV: R-2 = 0.976, RMSE = 7.1ml; EF: R-2 = 0.828, RMSE = 4.71%). Conclusion: Experimental results prove that the proposed method may be useful for the LV volume prediction task. Significance: The proposed method not only has application potential for cardiac diseases screening for large-scale CMR data, but also can be extended to other medical image research fields.