Abstract
Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our method significantly reduces inference time while preserving and further enhancing the quality of the outputs. Furthermore, this approach is highly adaptable, supporting various medical imaging modalities, conditioning mechanisms (such as class labels and masks), and different spatial dimensions, including 2D and 3D. Beyond image generation, it can also be applied to related tasks such as image enhancement. Our results demonstrate the efficiency and versatility of this framework, making it a promising advancement for medical imaging applications. Code with checkpoints and a synthetic dataset (beneficial for classification and segmentation) is now available on: this https URL.
Abstract (translated)
深度学习模型已成为各种医学应用的强大工具。然而，它们的成功依赖于大规模、高质量的数据集，由于隐私问题和昂贵的标注成本，这类数据集难以获得。生成模型（如扩散模型）通过合成医学图像提供了一种潜在解决方案，但其实际采用受到长推理时间的限制。在本文中，我们提出使用最优传输流匹配方法来加速图像生成过程。通过引入源分布与目标分布之间更直接的映射关系，我们的方法显著减少了推理时间，同时保持并进一步增强了输出的质量。 此外，该方法具有高度的适应性，支持各种医学成像模式、条件机制（如类别标签和掩码）以及不同空间维度（包括2D和3D）。除了图像生成之外，它还可以应用于诸如图像增强等相关任务。我们的结果展示了此框架在效率和多功能性方面的优势，使其成为医学影像应用中的一个有前景的发展方向。 代码及相关检查点与合成数据集（有利于分类和分割）现已公开于：[这个链接](this https URL)。
URL
https://arxiv.org/abs/2503.00266
