小模型比大模型更适合医学图像重建，自然图像训练更有效。
Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction
- 用小型残差网络替代复杂注意力结构，提升鲁棒性。
- 自然图像预训练模型在跨分布重建中表现优于医疗图像训练模型。
- 适合追求高效、泛化能力强的医学图像重建研究者。
扩散模型已成功应用于包括MRI和CT在内的多种逆问题重建。现有研究通常直接复用为无条件采样设计的大型模型，不做调整。我们通过两种不同的后验采样算法，实证表明此类大模型并非必需。最小模型（实质为残差网络）在分布内重建上表现接近注意力U-Net，且对分布外变化显著更鲁棒。此外，我们在自然图像上训练的模型在MRI和CT重建中表现良好，尤其在分布外场景下优于医疗图像训练模型。因此，我们强烈建议避免简单复用超大规模网络，并提倡根据任务适配模型复杂度。更重要的是，我们认为训练于自然图像数据是构建通用扩散先验的关键步骤。
原文摘要 · Abstract (English)
Diffusion model have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。