Data-driven and physics-informed adaptive temperatureestimation for oncological hyperthermia

This paper integrates physics-informed neural networks with gated recurrent units to leverage both physical modeling and data-driven learning to achieve accurate and generalizable solutions in sparse-data regimes. The approach targets robot-assisted superficial oncological hyperthermia treatment, retrieving temperature distributions along a monodimensional domain from boundary measurements with uncertain domain properties and sparse internal measurements. Validation encompasses both heat equation simulations and experimental scenarios.