Physics-driven Synthetic Data Learning for Biomedical Magnetic Resonance
This addresses data scarcity for researchers in biomedical imaging, but it is incremental as it builds on existing physics-driven synthesis methods.
The paper tackles the problem of insufficient training data in biomedical magnetic resonance by proposing imaging physics-based data synthesis (IPADS), which generates synthetic data using physical laws to enable scalable and privacy-preserving deep learning, with demonstrated applications in fast imaging and signal reconstruction.
Deep learning has innovated 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 without or with few real data. Following the physical law of magnetic resonance, IPADS generates signals from differential equations or analytical solution models, making the learning more scalable, explainable, and better protecting privacy. Key components of IPADS learning, including signal generation models, basic deep learning network structures, enhanced data generation, and learning methods are discussed. Great potentials of IPADS have been demonstrated by representative applications in fast imaging, ultrafast signal reconstruction and accurate parameter quantification. Finally, open questions and future work have been discussed.