In previous work, we introduced the Shape Memory Alloy actuator based Robot Mask that can be used to enhance the expressiveness of the face. The basic concept of that design was the pulling of the skin through wires attached to the face and we explained the human anatomy based criteria of selecting these pulling points and directions. In this paper, we describe a case study of using the Robot Mask to assist physiotherapy of a hemifacial paralyzed patient.Earlier we reported the general design criteria of the Robot Mask. However, the significant difference in shape and size of human head among different individuals demands further customization of the Robot Mask. In this research a number of adjustment and customization stages were employed, from the design level to the implementation level and this paper briefly describes them. We also explain a depth image sensor data based analyzing method, which can record dynamics of facial expression in a continuous manner. We then evaluate the effectiveness of the Robot Mask by analyzing the range sensor data. We show that, while providing quick responses, the Robot Mask can also reduce the asymmetry of a smiling face.