Deep learning-based methods have spearheaded the automatic analysis of echocardiographic images, taking advantage of the publication of multiple open access datasets annotated by experts (CAMUS being one of the largest public databases). However, these models are still considered unreliable by clinicians due to unresolved issues concerning i) the temporal consistency of their predictions, and ii) their ability to generalize across datasets. In this context, we propose a comprehensive comparison between the current best performing methods in medical/echocardiographic image segmentation, with a particular focus on temporal consistency and cross-dataset aspects. We introduce a new private dataset, named CARDINAL, of apical two-chamber and apical four-chamber sequences, with reference segmentation over the full cardiac cycle. We show that the proposed 3D nnU-Net outperforms alternative 2D and recurrent segmentation methods. We also report that the best models trained on CARDINAL, when tested on CAMUS without any fine-tuning, still manage to perform competitively with respect to prior methods. Overall, the experimental results suggest that with sufficient training data, 3D nnU-Net could become the first automated tool to finally meet the standards of an everyday clinical device.

翻译：基于深度学习的方法已引领超声心动图图像的自动分析，这得益于多个由专家标注的开放获取数据集的发布（CAMUS是最大的公共数据库之一）。然而，由于以下未解决问题，临床医生仍认为这些模型不可靠：i) 其预测的时间一致性，以及 ii) 其跨数据集的泛化能力。在此背景下，我们提出了当前医学/超声心动图图像分割中最优方法的全面比较，特别关注时间一致性和跨数据集方面。我们引入了一个名为CARDINAL的新私有数据集，包含心尖两腔和心尖四腔序列，并提供整个心动周期的参考分割。我们表明，所提出的3D nnU-Net优于替代的2D和循环分割方法。我们还报告，在CARDINAL上训练的最佳模型，在未经过任何微调的情况下测试CAMUS时，仍能与此前方法竞争。总体而言，实验结果表明，在拥有足够训练数据的情况下，3D nnU-Net可能成为首个满足日常临床设备标准的自动化工具。