解决2D扩散模型重建3D医学影像时的切片不连续问题
Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity
- 通过控制采样噪声一致性，实现切片间生成轨迹对齐
- 无需额外损失或计算，显著提升3D重建质量
- 即插即用，适合所有基于2D扩散模型的3D医学影像任务
3D医学成像在临床诊断和科研中需求迫切。当前扩散模型（DMs）因能学习丰富的高质量数据先验，已成为医学图像重建的有效工具。然而，在医学成像中学习3D数据分布仍具挑战，不仅因数据采集困难，还因训练过程计算负担重。常见做法是基于2D数据先验训练扩散模型，并堆叠2D切片以重建3D图像。但扩散采样的固有随机性导致重建体积出现严重的切片间不连续。现有方法通常沿z轴施加连续性正则化，引入敏感超参数且易造成过度平滑。本文重新审视扩散采样中的随机性来源，提出切片间一致随机性（ISCS），一种简单有效的策略，可在采样过程中促进切片间一致性。核心思想是控制扩散采样中随机噪声分量的一致性，从而对齐其采样轨迹，无需添加新损失项或优化步骤。重要的是，所提ISCS为即插即用设计，可无缝集成到任意2D训练的扩散模型3D重建流程中，无额外计算开销。在多个医学成像任务上的实验表明，该方法能有效提升基于2D扩散模型的3D医学成像性能。研究结果表明，控制切片间随机性是利用2D扩散先验实现高保真3D医学成像的合理且实用路径。代码已开源：https://github.com/duchenhe/ISCS。
原文摘要 · Abstract (English)
3D medical imaging is in high demand and essential for clinical diagnosis and scientific research. Currently, diffusion models (DMs) have become an effective tool for medical imaging reconstruction thanks to their ability to learn rich, high-quality data priors. However, learning the 3D data distribution with DMs in medical imaging is challenging, not only due to the difficulties in data collection but also because of the significant computational burden during model training. A common compromise is to train the DMs on 2D data priors and reconstruct stacked 2D slices to address 3D medical inverse problems. However, the intrinsic randomness of diffusion sampling causes severe inter-slice discontinuities of reconstructed 3D volumes. Existing methods often enforce continuity regularizations along the z-axis, which introduces sensitive hyper-parameters and may lead to over-smoothing results. In this work, we revisit the origin of stochasticity in diffusion sampling and introduce Inter-Slice Consistent Stochasticity (ISCS), a simple yet effective strategy that encourages interslice consistency during diffusion sampling. Our key idea is to control the consistency of stochastic noise components during diffusion sampling, thereby aligning their sampling trajectories without adding any new loss terms or optimization steps. Importantly, the proposed ISCS is plug-and-play and can be dropped into any 2D trained diffusion based 3D reconstruction pipeline without additional computational cost. Experiments on several medical imaging problems show that our method can effectively improve the performance of medical 3D imaging problems based on 2D diffusion models. Our findings suggest that controlling inter-slice stochasticity is a principled and practically attractive route toward high-fidelity 3D medical imaging with 2D diffusion priors. The code is available at: https://github.com/duchenhe/ISCS
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。