Marios Anthimopoulos1, Joachim Dehais2, Sergey Shevchik1, Botwey H Ransford1, David Duke3, Peter Diem4, Stavroula Mougiakakou5. 1. Diabetes Technology Research Group, ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland. 2. Diabetes Technology Research Group, ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland. 3. Diabetes Care, Roche Diagnostics Operations Inc, Indianapolis, IN, USA. 4. Department of Endocrinology, Diabetes & Clinical Nutrition, Bern University Hospital "Inselspital," Bern, Switzerland. 5. Diabetes Technology Research Group, ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland Department of Endocrinology, Diabetes & Clinical Nutrition, Bern University Hospital "Inselspital," Bern, Switzerland stavroula.mougiakakou@artorg.unibe.ch.
Abstract
BACKGROUND: Individuals with type 1 diabetes (T1D) have to count the carbohydrates (CHOs) of their meal to estimate the prandial insulin dose needed to compensate for the meal's effect on blood glucose levels. CHO counting is very challenging but also crucial, since an error of 20 grams can substantially impair postprandial control. METHOD: The GoCARB system is a smartphone application designed to support T1D patients with CHO counting of nonpacked foods. In a typical scenario, the user places a reference card next to the dish and acquires 2 images with his/her smartphone. From these images, the plate is detected and the different food items on the plate are automatically segmented and recognized, while their 3D shape is reconstructed. Finally, the food volumes are calculated and the CHO content is estimated by combining the previous results and using the USDA nutritional database. RESULTS: To evaluate the proposed system, a set of 24 multi-food dishes was used. For each dish, 3 pairs of images were taken and for each pair, the system was applied 4 times. The mean absolute percentage error in CHO estimation was 10 ± 12%, which led to a mean absolute error of 6 ± 8 CHO grams for normal-sized dishes. CONCLUSION: The laboratory experiments demonstrated the feasibility of the GoCARB prototype system since the error was below the initial goal of 20 grams. However, further improvements and evaluation are needed prior launching a system able to meet the inter- and intracultural eating habits.
BACKGROUND: Individuals with type 1 diabetes (T1D) have to count the carbohydrates (CHOs) of their meal to estimate the prandial insulin dose needed to compensate for the meal's effect on blood glucose levels. CHO counting is very challenging but also crucial, since an error of 20 grams can substantially impair postprandial control. METHOD: The GoCARB system is a smartphone application designed to support T1D patients with CHO counting of nonpacked foods. In a typical scenario, the user places a reference card next to the dish and acquires 2 images with his/her smartphone. From these images, the plate is detected and the different food items on the plate are automatically segmented and recognized, while their 3D shape is reconstructed. Finally, the food volumes are calculated and the CHO content is estimated by combining the previous results and using the USDA nutritional database. RESULTS: To evaluate the proposed system, a set of 24 multi-food dishes was used. For each dish, 3 pairs of images were taken and for each pair, the system was applied 4 times. The mean absolute percentage error in CHO estimation was 10 ± 12%, which led to a mean absolute error of 6 ± 8 CHO grams for normal-sized dishes. CONCLUSION: The laboratory experiments demonstrated the feasibility of the GoCARB prototype system since the error was below the initial goal of 20 grams. However, further improvements and evaluation are needed prior launching a system able to meet the inter- and intracultural eating habits.
Authors: A S Brazeau; H Mircescu; K Desjardins; C Leroux; I Strychar; J M Ekoé; R Rabasa-Lhoret Journal: Diabetes Res Clin Pract Date: 2012-11-10 Impact factor: 5.602
Authors: Fengqing Zhu; Marc Bosch; Insoo Woo; Sungye Kim; Carol J Boushey; David S Ebert; Edward J Delp Journal: IEEE J Sel Top Signal Process Date: 2010-08 Impact factor: 6.856
Authors: Melanie B Gillingham; Zoey Li; Roy W Beck; Peter Calhoun; Jessica Castle; Mark Clements; Eyal Dassau; Francis J Doyle; Robin L Gal; Peter Jacobs; Susana R Patton; Michael R Rickels; Michael Riddell; Corby K Martin Journal: Diabetes Technol Ther Date: 2020-09-29 Impact factor: 6.118
Authors: Katja A Schönenberger; Luca Cossu; Francesco Prendin; Giacomo Cappon; Jing Wu; Klaus L Fuchs; Simon Mayer; David Herzig; Andrea Facchinetti; Lia Bally Journal: Front Nutr Date: 2022-04-07
Authors: Daniel Rhyner; Hannah Loher; Joachim Dehais; Marios Anthimopoulos; Sergey Shevchik; Ransford Henry Botwey; David Duke; Christoph Stettler; Peter Diem; Stavroula Mougiakakou Journal: J Med Internet Res Date: 2016-05-11 Impact factor: 5.428