Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far, video generation has only been possible by providing input data that is as rich as the output data, e.g., image sequence plus conditioning in, video out. However, clinical documentation is usually scarce and only single images are reported and stored, thus retrospective patient-specific analysis or the generation of rich training data becomes impossible with current approaches. In this paper, we extend elucidated diffusion models for video modelling to generate plausible video sequences from single images and arbitrary conditioning with clinical parameters. We explore this idea within the context of echocardiograms by looking into the variation of the Left Ventricle Ejection Fraction, the most essential clinical metric gained from these examinations. We use the publicly available EchoNet-Dynamic dataset for all our experiments. Our image to sequence approach achieves an R2 score of 93%, which is 38 points higher than recently proposed sequence to sequence generation methods. A public demo is available here: bit.ly/3HTskPF. Code and models will be available at: https://github.com/HReynaud/EchoDiffusion.

翻译：图像合成有望为机器学习方法向临床实践的转化提供价值。通过合成数据，诸如模型鲁棒性、领域迁移、因果建模及操作员培训等基本问题变得易于处理。特别是，对于严重依赖操作员的模态（如超声成像），需要稳健的图像和视频生成框架。迄今为止，视频生成仅在提供的输入数据与输出数据同样丰富时才成为可能，例如，图像序列加上条件输入，输出视频。然而，临床记录通常较为稀缺，仅记录和存储单张图像，因此，现有方法无法实现回顾性患者特异性分析或生成丰富的训练数据。在本文中，我们扩展了解析扩散模型以进行视频建模，从而从单张图像和任意临床参数条件的结合中生成合理的视频序列。我们通过探究左心室射血分数的变化（这是从这些检查中获得的最关键的临床指标）来探索这一思想在超声心动图中的具体应用。我们使用公开可用的EchoNet-Dynamic数据集进行所有实验。我们的图像到序列方法实现了93%的R²得分，比近期提出的序列到序列生成方法高出38分。公开演示可在此处获取：bit.ly/3HTskPF。代码和模型将发布于：https://github.com/HReynaud/EchoDiffusion。