Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada.
Stephenson Cardiac Imaging Centre, Libin Cardiovascular Institute of Alberta, University of Calgary, Calgary, AB, USA.
Med Phys. 2019 Apr;46(4):1740-1751. doi: 10.1002/mp.13436. Epub 2019 Feb 28.
Accurate three-dimensional (3D) segmentation of myocardial replacement fibrosis (i.e., scar) is emerging as a potentially valuable tool for risk stratification and procedural planning in patients with ischemic cardiomyopathy. The main purpose of this study was to develop a semiautomated method using a 3D convolutional neural network (CNN)-based for the segmentation of left ventricle (LV) myocardial scar from 3D late gadolinium enhancement magnetic resonance (LGE-MR) images.
Our proposed CNN is built upon several convolutional and pooling layers aimed at choosing appropriate features from LGE-MR images to distinguish between myocardial scar and healthy tissues of the left ventricle. In contrast to previous methods that consider image intensity as the sole feature, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of unconventional features that separate scar from normal myocardium in the feature space. The first step of our pipeline was to manually delineate the left ventricular myocardium, which was used as the region of interest for scar segmentation. Our developed algorithm was trained using 265,220 volume patches extracted from ten 3D LGE-MR images, then was validated on 450,454 patches from a testing dataset of 24 3D LGE-MR images, all obtained from patients with chronic myocardial infarction. We evaluated our method in the context of several alternative methods by comparing algorithm-generated segmentations to manual delineations performed by experts.
Our CNN-based method reported an average Dice similarity coefficient (DSC) and Jaccard Index (JI) of 93.63% ± 2.6% and 88.13% ± 4.70%. In comparison to several previous methods, including K-nearest neighbor (KNN), hierarchical max flow (HMF), full width at half maximum (FWHM), and signal threshold to reference mean (STRM), the developed algorithm reported significantly higher accuracy for DSC with a P-value less than 0.0001.
Our experimental results demonstrated that our CNN-based proposed method yielded the highest accuracy of all contemporary LV myocardial scar segmentation methodologies, inclusive of the most widely used signal intensity-based methods, such as FWHM and STRM. To our knowledge, this is the first description of LV myocardial scar tissue segmentation from 3D LGE-MR images using a CNN-based method.
准确的三维（3D）心肌替代纤维化（即瘢痕）分割正成为一种有潜力的工具，可用于缺血性心肌病患者的风险分层和程序规划。本研究的主要目的是开发一种基于 3D 卷积神经网络（CNN）的半自动方法，用于从 3D 钆延迟增强磁共振（LGE-MR）图像中分割左心室（LV）心肌瘢痕。
我们提出的 CNN 建立在几个卷积和池化层上，旨在从 LGE-MR 图像中选择合适的特征，以区分心肌瘢痕和左心室的健康组织。与仅考虑图像强度作为唯一特征的先前方法不同，基于 CNN 的算法有可能通过创建在特征空间中区分瘢痕和正常心肌的非常规特征来提高瘢痕分割的准确性。我们的管道的第一步是手动描绘左心室心肌，这是瘢痕分割的感兴趣区域。我们使用从十个 3D LGE-MR 图像中提取的 265,220 个体积斑块对开发的算法进行训练，然后在来自 24 个 3D LGE-MR 图像的测试数据集的 450,454 个斑块上进行验证，所有这些图像均来自慢性心肌梗死患者。我们通过将算法生成的分割与专家进行的手动描绘进行比较，在几种替代方法的背景下评估我们的方法。
我们的基于 CNN 的方法报告的平均 Dice 相似系数（DSC）和 Jaccard 指数（JI）分别为 93.63%±2.6%和 88.13%±4.70%。与包括 K-最近邻（KNN）、层次最大流（HMF）、半峰全宽（FWHM）和信号阈值到参考均值（STRM）在内的几种先前方法相比，所开发的算法报告的 DSC 准确性显著更高，P 值小于 0.0001。
我们的实验结果表明，我们提出的基于 CNN 的方法的准确性高于所有当代 LV 心肌瘢痕分割方法，包括最广泛使用的基于信号强度的方法，如 FWHM 和 STRM。据我们所知，这是首次使用基于 CNN 的方法从 3D LGE-MR 图像中分割 LV 心肌瘢痕组织。
