MUMINS：元数据条件的不确定性感知医学图像下一状态合成
MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis
- Universitat de Barcelona（巴塞罗那大学）
- Barcelona Supercomputing Center (BSC)（巴塞罗那超级计算中心）
- Eurecat Centre Tecnològic de Catalunya（加泰罗尼亚Eurecat技术中心）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
MUMINS提出一种元数据条件的不确定性感知扩散框架，通过联合扩散基线扫描与残差并在单次反向过程中预测不确定性图，高效合成医学图像下一状态，在肺CT和脑MRI上匹配或超越专用方法。
中文摘要 AI 辅助
预测肿瘤生长和神经退行性变等解剖学变化是一项具有挑战性的生成视觉任务。形态演化相对于静态解剖是微妙的，高度个体化，并且本质上是随机的。现有方法面临若干问题：确定性网络忽略生物随机性，而标准扩散模型需要计算上昂贵的多遍采样来量化不确定性。我们提出MUMINS（元数据条件的不确定性感知医学图像下一状态合成），一种高效的扩散框架，它在单个反向扩散过程中联合扩散基线扫描及其随访残差，二者相加合成随访扫描，同时预测空间不确定性图。以时间间隔和相关元数据为条件，它通过在每次去噪步骤中动态重新注入基线作为软锚来保留精细解剖结构，并且负对数似然头学习不确定性图以明确标记易出错区域。该设计无需器官特异性启发式，同一架构通过数据集特定的重新训练在不同解剖部位间复用。大量评估表明，MUMINS的数据集特定重新训练在肺CT（PNG）和脑MRI（OASIS-3）上匹配或超越专门的领域特定最先进方法。项目页面：此HTTPS URL。
英文摘要
Forecasting anatomical changes such as tumor growth and neurodegeneration is a challenging generative vision task. Morphological evolution is subtle relative to static anatomy, highly patient-specific, and inherently stochastic. Existing methods struggle with several issues: deterministic networks ignore biological stochasticity, while standard diffusion models require computationally prohibitive multi-pass sampling to quantify uncertainty. We propose MUMINS (Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis), an efficient diffusion framework that jointly diffuses a baseline scan and its follow-up residual, summed to synthesize the follow-up scan, while concurrently predicting a spatial uncertainty map, in a single reverse diffusion process. Conditioned on the time interval and relevant metadata, it preserves fine-grained anatomy by dynamically re-injecting the baseline as a soft anchor at every denoising step, and a negative-log-likelihood head learns the uncertainty map to explicitly flag error-prone regions. Designed without organ-specific heuristics, the same architecture is reused across anatomies via separate, dataset-specific retraining. Extensive evaluations demonstrate that dataset-specific retraining of MUMINS matches or outperforms dedicated, domain-specific state-of-the-art methods on lung CT (PNG) and brain MRI (OASIS-3). Project page: https://github.com/aolivtous/MUMINS.
