Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)

2026-02-03

AI Summary

Quantitative molecular MRI lacks reliable uncertainty quantification for multi-parameter estimation, limiting its clinical credibility. This work proposes a physics-structured variational autoencoder (PS-VAE) that, for the first time, integrates a differentiable spin physics simulator into a variational inference framework, combined with self-supervised learning to efficiently generate voxel-wise posterior distributions of multiple parameters while explicitly capturing their interdependencies. The method enables real-time adaptive acquisition optimization and demonstrates excellent agreement with brute-force Bayesian analysis across diverse experiments. Moreover, it accelerates whole-brain multi-parameter quantification by several orders of magnitude, achieving a remarkable balance among accuracy, computational efficiency, and interpretability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• quantitative MRI
• uncertainty quantification
• magnetic resonance fingerprinting
• biophysical parameters
• clinical trustworthiness

Innovation

• Physics-Structured VAE
• Uncertainty Quantification
• Magnetic Resonance Fingerprinting
• Differentiable Physics Simulation
• Multi-parameter Posterior