Integration of an Image-Based Dietary Assessment Paradigm into Dietetic Training Improves Food Portion Estimates by Future Dietitians

Abstract

The use of image-based dietary assessments (IBDAs) has rapidly increased; however, there is no formalized training program to enhance the digital viewing skills of dieticians. An IBDA was integrated into a nutritional practicum course in the School of Nutrition and Health Sciences, Taipei Medical University Taiwan. An online IBDA platform was created as an off-campus remedial teaching tool to reinforce the conceptualization of food portion sizes. Dietetic students’ receptiveness and response to the IBDA, and their performance in food identification and quantification, were compared between the IBDA and real food visual estimations (RFVEs). No differences were found between the IBDA and RFVE in terms of food identification (67% vs. 71%) or quantification (±10% of estimated calories: 23% vs. 24%). A Spearman correlation analysis showed a moderate to high correlation for calorie estimates between the IBDA and RFVE (r ≥ 0.33~0.75, all p < 0.0001). Repeated IBDA training significantly improved students’ image-viewing skills [food identification: first semester: 67%; pretest: 77%; second semester: 84%) and quantification [±10%: first semester: 23%; pretest: 28%; second semester: 32%; and ±20%: first semester: 38%; pretest: 48%; second semester: 59%] and reduced absolute estimated errors from 27% (first semester) to 16% (second semester). Training also greatly improved the identification of omitted foods (e.g., condiments, sugar, cooking oil, and batter coatings) and the accuracy of food portion size estimates. The integration of an IBDA into dietetic courses has the potential to help students develop knowledge and skills related to “e-dietetics”.

A Novel Approach to Dining Bowl Reconstruction for Image-Based Food Volume Estimation

“…Even with a standard checkerboard (2D) placed beside the plate or bowl as a cue in every image, the mean percentage difference in portion size was still over 44% and less than one-third of the participants estimated food portion within 10% of the ground truth [36]. A similar conclusion was made in another study [68]. A reason for the relatively poor performance by the dietitian was likely due to the insufficient use of the cues provided.…”

“…While the computer prefers a complete 3D shape model as a volumetric reference, such as the interior surface of the bowl, the human prefers more intuitive cues, such as forks/spoons of known sizes, sizes of certain food components, or even human hands present in the image. Thus, how to maximize the amount of information in the provided cues by a human estimator is an interesting subject to study [68].…”

Validation of a Sustainable Diet Index among young Malaysian adults

“…However, Seconda et al (2019) found environment proxy to be better correlated with their SDI. The difference might be due to different indicators used in each index, different dietary patterns among the populations, and the different sources of carbon footprint data used in the calculation (Garnett et al, 2014;Seed, 2014;Ho et al, 2021).…”

“…The food image recognition and quantification executed by SFR were conducted manually by the researchers. The food images demonstrated acceptable relative validation and reliability for the macro-and micronutrients intakes when tested against the traditional 24hour diet recall (Ho et al, 2021).…”

Food Volume Estimation by Integrating 3D Image Projection and Manual Wire Mesh Transformations

“…mobile phones with multiple front facing cameras to obtain stereo images, is not yet common place or affordable [17]. Thus, there is ongoing research into developing methods to generate accurate 3D volume estimates from 2D images [10].…”