Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.
Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.
复制标题
DOI：
10.1016/j.media.2018.05.008
复制
发表时间：
2018-08
影响因子：
10.9
通讯作者：
Noble JA
中科院分区：
文献类型：
--
作者：
Vigneault DM;Xie W;Ho CY;Bluemke DA;Noble JA
二维稳态自由进动（SSFP）电影序列中左心室（LV）心肌和四个心腔的像素分割是广泛分析的重要预处理步骤。患者、临床视图、扫描仪和协议之间心脏的对比度、外观、方向和位置的可变性使得全自动语义分割成为众所周知的难题。在这里，我们介绍了Omega-Net（Omega-Net）：一种新型的卷积神经网络（CNN）架构，用于同时定位，转换为规范方向和语义分割。首先，对输入图像执行初始分割;其次，使用在该初始分割期间学习的特征来预测将输入图像变换为规范方向所需的参数;以及第三，对变换后的图像执行最终分割。在这项工作中，不同深度的神经网络被训练来检测三个临床视图（短轴，SA;四腔，4C;两腔，2C）中的任何一个中的五个前景类，而无需对被分割的视图的先验知识。这构成了一个更具挑战性的问题相比，以前的工作。使用三重交叉验证对肥厚型心肌病（HCM，N = 42）患者和健康对照受试者（N = 21）队列进行了架构训练。与没有定位或方向的U-Net分割相比，性能最佳的C-Net的网络性能（通过加权前景交叉联合（IoU）测量）得到了大幅改善（0.858 vs 0.834）。此外，为了与其他作品进行比较，在公开的2017年MICCAI自动心脏诊断挑战（ACDC）数据集上，使用五重交叉验证从头开始重新训练了MSN-Net。在LV和RV血池的分割方面，EST-Net优于最先进的方法，在LV心肌的分割方面表现略差。我们的结论是，这种架构代表了一个实质性的进步，比以前的方法，更普遍的生物医学图像分割的影响。
Pixelwise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady state free precession (SSFP) cine sequences is an essential preprocessing step for a wide range of analyses. Variability in contrast, appearance, orientation, and placement of the heart between patients, clinical views, scanners, and protocols makes fully automatic semantic segmentation a notoriously difficult problem. Here, we present Ω-Net (Omega-Net): A novel convolutional neural network (CNN) architecture for simultaneous localization, transformation into a canonical orientation, and semantic segmentation. First, an initial segmentation is performed on the input image; second, the features learned during this initial segmentation are used to predict the parameters needed to transform the input image into a canonical orientation; and third, a final segmentation is performed on the transformed image. In this work, Ω-Nets of varying depths were trained to detect five foreground classes in any of three clinical views (short axis, SA; four-chamber, 4C; two-chamber, 2C), without prior knowledge of the view being segmented. This constitutes a substantially more challenging problem compared with prior work. The architecture was trained using three-fold cross-validation on a cohort of patients with hypertrophic cardiomyopathy (HCM, N = 42) and healthy control subjects (N = 21). Network performance, as measured by weighted foreground intersection-over-union (IoU), was substantially improved for the best-performing Ω-Net compared with U-Net segmentation without localization or orientation (0.858 vs 0.834). In addition, to be comparable with other works, Ω-Net was retrained from scratch using five-fold cross-validation on the publicly available 2017 MICCAI Automated Cardiac Diagnosis Challenge (ACDC) dataset. The Ω-Net outperformed the state-of-the-art method in segmentation of the LV and RV blood-pools, and performed slightly worse in segmentation of the LV myocardium. We conclude that this architecture represents a substantive advancement over prior approaches, with implications for biomedical image segmentation more generally.
登录
查看更多内容
影响因子：
4.8
作者：
Dieleman, Sander;Willett, Kyle W.;Dambre, Joni
通讯作者：
Dambre, Joni
DOI：
10.1007/s10334-015-0521-4
发表时间：
2016-04
期刊：
Magma (New York, N.Y.)
影响因子：
--
作者：
Peng P;Lekadir K;Gooya A;Shao L;Petersen SE;Frangi AF
通讯作者：
Frangi AF
影响因子：
24
作者：
Ho CY;Day SM;Colan SD;Russell MW;Towbin JA;Sherrid MV;Canter CE;Jefferies JL;Murphy AM;Cirino AL;Abraham TP;Taylor M;Mestroni L;Bluemke DA;Jarolim P;Shi L;Sleeper LA;Seidman CE;Orav EJ;HCMNet Investigators
通讯作者：
HCMNet Investigators
DOI：
10.1080/21681163.2016.1149104
发表时间：
2018-01-01
影响因子：
1.6
作者：
Xie, Weidi;Noble, J. Alison;Zisserman, Andrew
通讯作者：
Zisserman, Andrew
影响因子：
10.9
作者：
Tan, Li Kuo;Liew, Yih Miin;McLaughlin, Robert A.
通讯作者：
McLaughlin, Robert A.