arXiv：cs.LG· Alex Finkelstein, Ron Moneta, Or Zohar, Michal Rivlin, Moritz Zaiss, Dinora Friedmann Morvinski, Or Perlman·· 4 小时前AI 评分36
PS-VAE：用物理结构变分自编码器实现定量分子 MRI 多参数不确定性映射
Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)
AI 导读
研究者提出物理结构变分自编码器（PS-VAE），用于快速提取体素级多参数后验分布，将可微分自旋物理模拟器与自监督学习结合，输出可捕捉参数间相关性的完整协方差。该方法在 CEST 与半固体 MT 分子 MRF 研究中经体外模体、荷瘤小鼠、健康志愿者及胶质母细胞瘤受试者验证，结果与暴力贝叶斯分析吻合，全脑定量提速数个数量级。监测多参数后验动态还可为协议优化和实时自适应采集提供参考。
正文
Abstract:Quantitative imaging methods, such as magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue parameters from signal evolutions. However, the pattern-matching algorithms or neural networks used in such inverse problems often lack principled uncertainty quantification, which limits the trustworthiness and transparency, required for clinical acceptance. Here, we describe a physics-structured variational autoencoder (PS-VAE) designed for rapid extraction of voxelwise multi-parameter posterior distributions. Our approach integrates a differentiable spin physics simulator with self-supervised learning, and provides a full covariance that captures the inter-parameter correlations of the latent biophysical space. The method was validated in a multi-proton pool chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) molecular MRF study, across in-vitro phantoms, tumor-bearing mice, healthy human volunteers, and a subject with glioblastoma. The resulting multi-parametric posteriors are in good agreement with those calculated using a brute-force Bayesian analysis, while providing an orders-of-magnitude acceleration in whole brain quantification. In addition, we demonstrate how monitoring the multi-parameter posterior dynamics across progressively acquired signals provides practical insights for protocol optimization and may facilitate real-time adaptive acquisition.
| Comments: | Accepted by IEEE Transactions on Medical Imaging. This project was funded by the European Union (ERC, BabyMagnet, project no. 101115639). Views and opinions expressed are, however, those of the authors only and do not necessarily reflect those of the European Union or the European Research Council. Neither the European Union nor the granting authority can be held responsible for them |
| Subjects: | Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Medical Physics (physics.med-ph) |
| Cite as: | arXiv:2602.03317 [stat.ML] |
| (or arXiv:2602.03317v2 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2602.03317 arXiv-issued DOI via DataCite |
|
| Journal reference: | A. Finkelstein et al., "Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)", IEEE Transactions on Medical Imaging, 2026 |
| Related DOI: | https://doi.org/10.1109/TMI.2026.3740952
DOI(s) linking to related resources |
Submission history
From: Alex Finkelstein [view email]
[v1]
Tue, 3 Feb 2026 09:46:55 UTC (9,374 KB)
[v2]
Wed, 7 Oct 2026 08:05:00 UTC (7,962 KB)
来源：arXiv：cs.LG · arxiv.org