Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
This work addresses the practical adoption barrier of generative models in medical imaging by improving speed and quality, though it is incremental as it builds on existing flow matching methods.
The paper tackled the slow inference times of diffusion models for medical image synthesis by proposing an optimal transport flow matching approach, which significantly reduced inference time while preserving and enhancing output quality, as demonstrated across various medical imaging modalities and tasks.
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: https://github.com/milad1378yz/MOTFM.