Buoso Stefano, Stoeck Christian T, Kozerke Sebastian
Institute for Biomedical Engineering, ETH Zurich and University Zurich, Zurich, Switzerland.
Institute for Biomedical Engineering, ETH Zurich and University Zurich, Zurich, Switzerland; Center for Preclinical Development, University Hospital Zurich and University Zurich, Zurich, Switzerland.
J Cardiovasc Magn Reson. 2025 Feb 26;27(1):101869. doi: 10.1016/j.jocmr.2025.101869.
Three-dimensional (3D) tagged magnetic resonance (MR) imaging enables in-vivo quantification of cardiac motion. While deep learning methods have been developed to analyze these images, they have been restricted to two-dimensional datasets. We present a deep learning approach specifically designed for displacement analysis of 3D cardiac tagged MR images.
We developed two neural networks to predict left-ventricular motion throughout the cardiac cycle. Networks were trained using synthetic 3D tagged MR images, generated by combining a biophysical left-ventricular model with an analytical MR signal model. Network performance was initially validated on synthetic data, including assessment of signal-to-noise ratio sensitivity. The networks were then retrospectively evaluated on an in-vivo external validation human dataset and an in-vivo porcine study.
For the external validation dataset, predicted displacements deviated from manual tracking by median (interquartile range) values of 0.72 (1.17), 0.81 (1.64), and 1.12 (4.17) mm in x, y, and z directions, respectively. In the porcine dataset, strain measurements showed median (interquartile range) differences from manual annotations of 0.01 (0.04), 0.01 (0.06), and -0.01 (0.18) for circumferential, longitudinal, and radial components, respectively. These strain values are within physiological ranges and demonstrate superior performance of the network approach compared to existing 3D tagged image analysis methods.
The method enables rapid analysis times of approximately 10 s per cardiac phase, making it suitable for large cohort investigations.
三维（3D）标记磁共振（MR）成像能够对心脏运动进行体内定量分析。虽然已经开发出深度学习方法来分析这些图像，但它们仅限于二维数据集。我们提出了一种专门为3D心脏标记MR图像的位移分析设计的深度学习方法。
我们开发了两个神经网络来预测整个心动周期中的左心室运动。使用合成的3D标记MR图像对网络进行训练，这些图像是通过将生物物理左心室模型与分析MR信号模型相结合生成的。网络性能最初在合成数据上进行验证，包括评估信噪比敏感性。然后在体内外部验证人类数据集和体内猪研究中对网络进行回顾性评估。
对于外部验证数据集，预测位移在x、y和z方向上与手动跟踪的偏差分别为中位数（四分位间距）0.72（1.17）、0.81（1.64）和1.12（4.17）mm。在猪数据集中，圆周、纵向和径向分量的应变测量值与手动标注的中位数（四分位间距）差异分别为0.01（0.04）、0.01（0.06）和 -0.01（0.18）。这些应变值在生理范围内，并且与现有的3D标记图像分析方法相比，证明了网络方法的优越性能。
该方法每个心动周期的分析时间约为10秒，适用于大型队列研究。
