A distance map regularized CNN for cardiac cine MR image segmentation
A distance map regularized CNN for cardiac cine MR image segmentation
复制标题
DOI：
10.1002/mp.13853
复制
发表时间：
2019-12-01
期刊：
影响因子：
3.8
通讯作者：
Yaniv, Ziv
中科院分区：
文献类型：
--
作者：
Dangi, Shusil;Linte, Cristian A.;Yaniv, Ziv
用途：心脏图像分割是生成个性化心脏模型和量化心脏性能参数的关键过程。由于正常和异常解剖结构以及成像协议的可变性，从心脏电影MR图像中全自动分割左心室（LV）、右心室（RV）和心肌具有挑战性。本研究提出了一种基于多任务学习（MTL）的卷积神经网络（CNN）的正则化，以获得准确的分割的心脏结构从电影MR images.Methods：我们训练CNN网络执行语义分割的主要任务，沿着与像素距离图回归的同时，辅助任务。该网络还预测与这两个任务相关的不确定性，使得它们的损失由它们相应的不确定性的倒数加权。因此，在训练过程中，具有较高不确定性的任务权重较小，反之亦然。提出的距离映射正则化器是一个解码器网络，添加到现有CNN架构的瓶颈层，便于网络学习鲁棒的全局特征。在训练后移除正则化块，使得网络参数的原始数量不改变。训练后的网络输出每像素分割时，提供一个新的患者电影MR图像作为input.Results：我们表明，所提出的正则化方法提高了相应的国家的最先进的CNN架构的二进制和多类分割性能。对两个公开可用的心脏电影MRI数据集进行了评价，得出平均Dice系数为0.84 +/- 0.03和0.91 +/- 0.04。我们还证明了距离映射正则化网络在跨数据集分割上的泛化性能得到了改善，心肌Dice系数从0.56 +/- 0.28提高到0.80 +/-0.14，提高了42%。结论：我们提出了一种从电影MR图像中准确分割心脏结构的方法。我们的实验验证，该方法超过了现有的三个国家的最先进的方法的分割性能。此外，通常用作诊断生物标志物的几个心脏指数，特别是使用我们的方法计算的血池体积、心肌质量和射血分数，与从参考、地面实况分割计算的指数更好地相关。因此，所提出的方法有可能成为一种非侵入性的筛选和诊断工具，用于各种心脏状况的临床评估，以及一个可靠的援助，用于生成患者特定的心脏解剖模型，用于治疗计划，模拟和指导。(C)2019年美国医学物理学家协会
Purpose: Cardiac image segmentation is a critical process for generating personalized models of the heart and for quantifying cardiac performance parameters. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV), and the myocardium from cardiac cine MR images is challenging due to variability of the normal and abnormal anatomy, as well as the imaging protocols. This study proposes a multi-task learning (MTL)-based regularization of a convolutional neural network (CNN) to obtain accurate segmenation of the cardiac structures from cine MR images.Methods: We train a CNN network to perform the main task of semantic segmentation, along with the simultaneous, auxiliary task of pixel-wise distance map regression. The network also predicts uncertainties associated with both tasks, such that their losses are weighted by the inverse of their corresponding uncertainties. As a result, during training, the task featuring a higher uncertainty is weighted less and vice versa. The proposed distance map regularizer is a decoder network added to the bottleneck layer of an existing CNN architecture, facilitating the network to learn robust global features. The regularizer block is removed after training, so that the original number of network parameters does not change. The trained network outputs per-pixel segmentation when a new patient cine MR image is provided as an input.Results: We show that the proposed regularization method improves both binary and multi-class segmentation performance over the corresponding state-of-the-art CNN architectures. The evaluation was conducted on two publicly available cardiac cine MRI datasets, yielding average Dice coefficients of 0.84 +/- 0.03 and 0.91 +/- 0.04. We also demonstrate improved generalization performance of the distance map regularized network on cross-dataset segmentation, showing as much as 42% improvement in myocardium Dice coefficient from 0.56 +/- 0.28 to 0.80 +/- 0.14.Conclusions: We have presented a method for accurate segmentation of cardiac structures from cine MR images. Our experiments verify that the proposed method exceeds the segmentation performance of three existing state-of-the-art methods. Furthermore, several cardiac indices that often serve as diagnostic biomarkers, specifically blood pool volume, myocardial mass, and ejection fraction, computed using our method are better correlated with the indices computed from the reference, ground truth segmentation. Hence, the proposed method has the potential to become a non-invasive screening and diagnostic tool for the clinical assessment of various cardiac conditions, as well as a reliable aid for generating patient specific models of the cardiac anatomy for therapy planning, simulation, and guidance. (C) 2019 American Association of Physicists in Medicine