Physics-Informed Artificial Intelligence for Biomedical Sensing, Imaging, and Signal Interpretation

Recent advances in artificial intelligence have transformed biomedical sensing and imaging, yet many data-driven models remain limited by poor interpretability, high data requirements, and reduced robustness when deployed in real-world clinical and health settings. Physics-informed artificial intelligence (PIAI) offers a promising paradigm by integrating first-principles models, physical constraints, and domain knowledge directly into learning frameworks, enabling more reliable, data-efficient, and explainable solutions for biomedical systems.This Research Topic aims to bring together methodological innovations and applied studies that leverage physics-informed AI for biomedical sensing, imaging, and signal interpretation. Of particular interest are approaches that combine mechanistic models of signal generation and propagation (e.g., electromagnetic, acoustic, optical, or electrophysiological processes) with machine learning techniques to improve inference, reconstruction, classification, and decision-making in complex biological environments. By grounding AI models in physical laws and system dynamics, such approaches can enhance generalizability across subjects, devices, and acquisition settings while supporting clinical trust and translational impact.We welcome contributions spanning theory, algorithms, system design, and applications, including but not limited to physics-informed neural networks, hybrid model-based and data-driven methods, inverse problem formulations, uncertainty-aware learning, and multimodal fusion strategies. Application domains may include radiofrequency and microwave sensing, biomedical imaging, wearable and ambient sensing, physiological monitoring, and non-invasive or contactless health assessment. Studies addressing validation, interpretability, robustness, and deployment in real-world biomedical or healthcare contexts are particularly encouraged.By bringing together advances in physics-informed learning with biomedical sensing and imaging, this Research Topic seeks to highlight emerging principles, tools, and applications that move AI-enabled bioengineering toward more trustworthy, efficient, and clinically meaningful solutions. Topic editors: Giuseppe Maruccio, Myles Joshua Toledo Tan Source: https://www.frontiersin.org/research-topics/82625/physics-informed-artificial-intelligence-for-biomedical-sensing-imaging-and-signal-interpretation