Development of Tracking System for Swallowing Movement Using Optical Flow

Naomi Yagi, Ryosuke Nishihara, Naoko Kawamura, Hitoshi Maezawa, Hideki Kashioka, Masayuki Hirata, Toshio Yanagida, Yoshitada Sakai, Yutaka Hata

Abstract: Currently, population in Japan has been aging at a speed unparalleled in other countries, and countermeasures against aging population and the worsening of disease for people with disabilities have become urgent issues. Pneumonia and aspiration pneumonia are the leading causes of death. It is said that swallowing function tends to decline from around age of 40, however it is important to keep it in good condition without deteriorating function as much as possible. The gold standard for swallowing functional evaluation is swallowing contrast testing, however X-ray exposure disables to repeat testing. In addition, Repetitive Saliva Swallowing Test (RSST) of screening test is difficult for self-check. Therefore, in this study, we develop a system to self-evaluate swallowing ability for keeping swallowing function healthy. It is proposed by applying optical flow and artificial intelligence of DeepLabcut. As a result, we were able to visualize movement of larynx during swallowing.