Developing tongue coating status assessment using image recognition with deep learning.

PURPOSE: To build an image recognition network to evaluate tongue coating status. METHODS: Two image recognition networks were built: one for tongue detection and another for tongue coating classification. Digital tongue photographs were used to develop both networks; images from 251 (178 women, 74.7±6.6 years) and 144 older adults (83 women, 73.8±7.3 years) who volunteered to participate were used for the tongue detection network and coating classification network, respectively. The learning objective of the tongue detection network is to extract a rectangular region that includes the tongue. You-Only-Look-Once (YOLO) v2 was used as the detection network, and transfer learning was performed using ResNet-50. The accuracy was evaluated by calculating the intersection over the union. For tongue coating classification, the rectangular area including the tongue was divided into a grid of 7×7. Five experienced panelists scored the tongue coating in each area using one of five grades, and the tongue coating index (TCI) was calculated. Transfer learning for tongue coating grades was performed using ResNet-18, and the TCI was calculated. Agreement between the panelists and network for the tongue coating grades in each area and TCI was evaluated using the kappa coefficient and intraclass correlation, respectively. RESULTS: The tongue detection network recognized the tongue with a high intersection over union (0.885±0.081). The tongue coating classification network showed high agreement with tongue coating grades and TCI, with a kappa coefficient of 0.826 and an intraclass correlation coefficient of 0.807, respectively. CONCLUSIONS: Image recognition enables simple and detailed assessment of tongue coating status.

Features of Masticatory Behaviors in Older Adults with Oral Hypofunction: A Cross-Sectional Study.

Although many studies have shown the relationships between oral function and nutrition and health, few reports have investigated the masticatory behaviors of older people. This study aimed to clarify the relationships between oral function and the masticatory behaviors and features of masticatory behaviors with oral hypofunction. A total of 98 community-dwelling independent older adults participated. Seven oral conditions related to oral hypofunction were examined, and the masticatory behaviors when consuming a rice ball were measured. The participants were divided into two groups according to the criteria for oral hypofunction, and the masticatory behaviors were compared. Furthermore, the relationship between masticatory performance and the number of chews was investigated. The chewing rate of the oral hypofunction group was slower than that of the no oral hypofunction group, but there was no difference in the number of chews and chewing time. The decreased tongue-lip motor function group showed a slower chewing rate, and the decreased tongue pressure group showed a smaller number of chews and shorter chewing time. No significant correlation was observed between masticatory performance and behavior. In conclusion, older adults with oral hypofunction chewed slowly due to decreased dexterity, while, even if oral and masticatory function decreased, no compensatory increase in the number of chews was observed.

Physical fitness and oral function in community-dwelling older people: a pilot study.

OBJECTIVE: The aim of the present study was to quantify the relation between physical fitness and oral function, including tongue and lip movements. BACKGROUND: Physical fitness and oral function influence quality of life and activities of daily living in older individuals. Occlusal contact and mastication performance are associated with physical fitness, but the association between tongue and lip movements and physical fitness is unclear. MATERIAL AND METHODS: Sixty-six independent community-dwelling older individuals (24 men, 42 women; mean age, 70.3 ± 5.9 years) participated in this study. Measures of physical fitness were the one-leg standing time with eyes open, the functional reach test, anteflexion, the timed up and go test, and grip strength. Measures of oral function were tongue pressure, lip pressure, tongue movement from side to side, the repetitive saliva-swallowing test (RSST), oral diadochokinesis and masticatory efficiency. Multiple regression analysis was used to quantify the relation between physical fitness and oral function. RESULTS: After adjustment for age, sex, BMI, exercise habits and number of remaining teeth, the tongue movement from side to side and/or oral diadochokinesis were chosen as significant factors in each physical fitness measurement. Furthermore, the lip pressure and masticatory efficiency were associated with handgrip strength. CONCLUSION: Oral function, including tongue and lip movements, was associated with physical fitness in older people in this study. Tongue dexterity as characterised by tongue movement from side to side and oral diadochokinesis particularly associated with physical fitness.