A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI
A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI
复制标题
DOI：
10.1016/j.media.2016.01.005
复制
发表时间：
2016-05-01
影响因子：
10.9
通讯作者：
Jafarkhani, Hamid
中科院分区：
文献类型：
--
作者：
Avendi, M. R.;Kheradvar, Arash;Jafarkhani, Hamid
从心脏磁共振成像（MRI）数据集分割左心室（LV）是计算心室容积和射血分数等临床指标的重要步骤。在这项工作中，我们采用深度学习算法与可变形模型相结合，从短轴心脏MRI数据集开发和评估全自动LV分割工具。该方法采用深度学习算法从地面真实数据中学习分割任务。卷积网络被用来自动检测MRI数据集中的左心室。堆叠的自动编码器用于推断LV形状。推断的形状被并入到可变形模型中，以提高分割的准确性和鲁棒性。我们使用来自MICCAI 2009 LV分割挑战的45个心脏MR数据集验证了我们的方法，并表明它优于最先进的方法。实现了与地面实况的极好一致。验证指标，良好轮廓的百分比，Dice指标，平均垂直距离和一致性，计算为96.69%，0.94，1.81 mm和0.86，与79.2 - 95.62%，0.87-0.9，1.76-2.97 mm和0.67-0.78，分别通过其他方法获得。(C)2016爱思唯尔B. V.保留所有权利。
Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2 95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively. (C) 2016 Elsevier B.V. All rights reserved.