Publication: Feasibility Study of an Automated Carbohydrate Estimation System Using Thai Food Images in Comparison With Estimation by Dietitians
Issued Date
2021-10-18
Resource Type
ISSN
2296861X
Other identifier(s)
2-s2.0-85118638831
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Frontiers in Nutrition. Vol.8, (2021)
Suggested Citation
Phawinpon Chotwanvirat, Narit Hnoohom, Nipa Rojroongwasinkul, Wantanee Kriengsinyos Feasibility Study of an Automated Carbohydrate Estimation System Using Thai Food Images in Comparison With Estimation by Dietitians. Frontiers in Nutrition. Vol.8, (2021). doi:10.3389/fnut.2021.732449 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/75565
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Feasibility Study of an Automated Carbohydrate Estimation System Using Thai Food Images in Comparison With Estimation by Dietitians
Other Contributor(s)
Abstract
Carbohydrate counting is essential for well-controlled blood glucose in people with type 1 diabetes, but to perform it precisely is challenging, especially for Thai foods. Consequently, we developed a deep learning-based system for automatic carbohydrate counting using Thai food images taken from smartphones. The newly constructed Thai food image dataset contained 256,178 ingredient objects with measured weight for 175 food categories among 75,232 images. These were used to train object detector and weight estimator algorithms. After training, the system had a Top-1 accuracy of 80.9% and a root mean square error (RMSE) for carbohydrate estimation of <10 g in the test dataset. Another set of 20 images, which contained 48 food items in total, was used to compare the accuracy of carbohydrate estimations between measured weight, system estimation, and eight experienced registered dietitians (RDs). System estimation error was 4%, while estimation errors from nearest, lowest, and highest carbohydrate among RDs were 0.7, 25.5, and 7.6%, respectively. The RMSE for carbohydrate estimations of the system and the lowest RD were 9.4 and 10.2, respectively. The system could perform with an estimation error of <10 g for 13/20 images, which placed it third behind only two of the best performing RDs: RD1 (15/20 images) and RD5 (14/20 images). Hence, the system was satisfactory in terms of accurately estimating carbohydrate content, with results being comparable with those of experienced dietitians.