Physics-Driven Synthetic Data Learning for Biomedical Magnetic Resonance: The imaging physics-based data synthesis paradigm for artificial intelligence

Deep learning (DL) has driven innovation in the field of computational imaging. One of its bottlenecks is unavailable or insufficient training data. This article reviews an emerging paradigm, imaging physics-based data synthesis (IPADS), that can provide huge training data in biomedical magnetic resonance (MR) without or with few real data. Following the physical law of MR, IPADS generates signals from differential equations or analytical solution models, making learning more scalable and explainable and better protecting privacy. Key components of IPADS learning, including signal generation models, basic DL network structures, enhanced data generation, and learning methods, are discussed. Great IPADS potential has been demonstrated by representative applications in fast imaging, ultrafast signal reconstruction, and accurate parameter quantification. Finally, open questions and future work are discussed.

Automated summary

Deep learning has driven innovation in computational imaging, but it often lacks sufficient training data. This article reviews imaging physics-based data synthesis (IPADS), an emerging paradigm that can provide large amounts of training data in biomedical magnetic resonance (MR), even without or with minimal real data. IPADS generates signals based on the physical law of MR, making learning more scalable, explainable, and privacy-preserving. The article discusses key components of IPADS learning, including signal generation models, basic DL network structures, enhanced data generation, and learning methods. Representative applications in fast imaging, ultrafast signal reconstruction, and accurate parameter quantification demonstrate the great potential of IPADS. Finally, open questions and future work are discussed.