Cardiac segmentation from magnetic resonance imaging (MRI) is one of the essential tasks in analyzing the anatomy and function of the heart for the assessment and diagnosis of cardiac diseases. However, cardiac MRI generates hundreds of images per scan, and manual annotation of them is challenging and time-consuming, and therefore processing these images automatically is of interest. This study proposes a novel end-to-end supervised cardiac MRI segmentation framework based on a diffeomorphic deformable registration that can segment cardiac chambers from 2D and 3D images or volumes. To represent actual cardiac deformation, the method parameterizes the transformation using radial and rotational components computed via deep learning, with a set of paired images and segmentation masks used for training. The formulation guarantees transformations that are invertible and prevents mesh folding, which is essential for preserving the topology of the segmentation results. A physically plausible transformation is achieved by employing diffeomorphism in computing the transformations and activation functions that constrain the range of the radial and rotational components. The method was evaluated over three different data sets and showed significant improvements compared to exacting learning and non-learning based methods in terms of the Dice score and Hausdorff distance metrics.

中文翻译：

---

基于深度学习的心脏图像分割微分像图像配准参数化

磁共振成像（MRI）的心脏分割是分析心脏的解剖结构和功能以评估和诊断心脏病的基本任务之一。然而，心脏 MRI 每次扫描会生成数百张图像，对它们进行手动注释具有挑战性且耗时，因此自动处理这些图像很有意义。本研究提出了一种基于微分同形变形配准的新型端到端监督心脏 MRI 分割框架，该框架可以从 2D 和 3D 图像或体积中分割心腔。为了表示实际的心脏变形，该方法使用通过深度学习计算的径向和旋转分量来参数化变换，并使用一组配对图像和用于训练的分割掩模。该公式保证了变换是可逆的并防止网格折叠，这对于保留分割结果的拓扑至关重要。通过在计算约束径向和旋转分量范围的变换和激活函数时采用微分同胚来实现物理上合理的变换。该方法在三个不同的数据集上进行了评估，与基于严格学习和非学习的方法相比，在 Dice 分数和 Hausdorff 距离度量方面显示出显着的改进。