The microwave-assisted thermal process is a high-efficiency drying method and is promising to be applied in the food industry. However, the prediction of the thermal treatment results from such a dynamic and complicated process can be difficult. Additionally, the determination of the optimal drying parameters, such as drying temperature, microwave power, and drying time for optimized performance can also be hard. Recently, extensive research has been focusing on the use of artificial neural network (ANN) models in the laboratory-scale microwave drying processes and has shown the feasibility of such application. As a regression tool, the ANN models have been widely used in predicting drying performance; when integrated with additional optimizing algorithms, the ANN models could be used for drying parameter optimization; and when combined with real-time measuring techniques (e.g. nuclear magnetic resonance), the ANN models could be used for monitoring and controlling the drying process in a dynamic sense. Future research could focus on testing the developed ANN models in industrial-scale microwave drying processes and applying the ANN models in microwave drying kinetics research for optimizing the dynamic drying processes.