Multi-parameter molecular MRI quantification using physics-informed self-supervised learning

• Published in: Communications physics Vol. 8; no. 1; pp. 164 - 11
• Main Authors: Finkelstein, Alex, Vladimirov, Nikita, Zaiss, Moritz, Perlman, Or
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 15.04.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 631/57/2266; 639/766/930/2735; Brain; Differential equations; Inverse problems; Machine learning; Magnetic resonance imaging; Medical imaging; Neural networks; Ordinary differential equations; Parameter estimation; Physics; Physics and Astronomy; Self-supervised learning; Semisolids; System dynamics
• DOI: 10.1038/s42005-025-02063-8
• ISSN: 2399-3650

Biophysical model fitting plays a key role in obtaining quantitative parameters from physiological signals and images. However, the model complexity for molecular magnetic resonance imaging (MRI) often translates into excessive computation time, which makes clinical use impractical. Here, we present a generic computational approach for solving the parameter extraction inverse problem posed by ordinary differential equation (ODE) modeling coupled with experimental measurement of the system dynamics. This is achieved by formulating a numerical ODE solver to function as a step-wise analytical one, thereby making it compatible with automatic differentiation-based optimization. This enables efficient gradient-based model fitting, and provides a new approach to parameter quantification based on self-supervised learning from a single data observation. The neural-network-based train-by-fit pipeline was used to quantify semisolid magnetization transfer (MT) and chemical exchange saturation transfer (CEST) amide proton exchange parameters in the human brain, in an in-vivo molecular MRI study (n = 4). The entire pipeline of the first whole brain quantification was completed in 18.3 ± 8.3 minutes. Reusing the single-subject-trained network for inference in new subjects took 1.0 ± 0.2 s, to provide results in agreement with literature values and scan-specific fit results. Quantitative molecular imaging extracts biophysical parameter maps by solving physics-based inverse problems. This work develops AI-driven methods to accelerate and stabilize multi-parameter estimation across millions of brain pixels.