Real-Time Prediction of Temperature for Electromagnetic Heating Therapy in Deep-Seated Tissue

This paper aims to develop a mathematical model for predicting the temperature response of tissues in electromagnetic heating therapy (EHT), when using a magnetic flux concentrator to improve heating efficiency. EHT has two critical challenges when applied to deep-seated tissue heating, i.e., the temperature might not be accurately measured and the magnetic field intensity decreases with increasing depth. The finite-element method (FEM) is suitable for coupled analysis with electromagnetic fields and heat transfer, which can be used to predict temperature profiles in deep tissue implanted with magnetic materials. To improve the accuracy of the FEM model, an adaptive network fuzzy inference system (ANFIS) model is implemented on the basis of measured data and simulated data, which were generated by the FEM model. The ANFIS model can provide a large number of testing data to optimize the parameters in the FEM model; moreover, it can be used to expedite the optimization process.