Portion Size Estimation Research Articles

Evaluating User Experiences and Preferred Features of a Web-Based 24-Hour Dietary Assessment Tool: Usability Study.

Intake24, a web-based 24-hour dietary recall tool developed in the United Kingdom, was adapted for use in New Zealand (Intake24-NZ) through the addition of a New Zealand food list, portion size images, and food composition database. Owing to the customizations made, a thorough evaluation of the tool's usability was required. Detailed qualitative usability studies are well suited to investigate any challenges encountered while completing a web-based 24-hour recall and provide meaningful data to inform enhancements to the tool. This study aims to evaluate the usability of Intake24-NZ and identify improvements to enhance both the user experience and the quality of dietary intake data collected. We used a mixed methods approach comprising two components: (1) completion of a single 24-hour dietary recall using Intake24-NZ with both screen observation recordings and collation of verbal participant feedback on their experience and (2) a survey. A total of 37 participants aged ≥11 years self-completed the dietary recall and usability survey (men and boys: 14/37, 38% and women and girls: 23/37, 62%; Māori: 10/37, 27% and non-Māori: 27/37, 73%). Although most (31/37, 84%) reported that Intake24-NZ was easy to use and navigate, data from the recorded observations and usability survey revealed challenges related to the correct use of search terms, search results obtained (eg, type and order of foods displayed), portion size estimation, and associated food prompts (eg, did you add milk to your tea?). This comprehensive usability study identified challenges experienced by users in completing a dietary recall in Intake24-NZ. The results informed a series of improvements to enhance user experience and the quality of dietary data collected with Intake24-NZ, including adding new foods to the food list, optimizing the search function and ordering of search results, creating new portion size images, and providing clearer instructions to the users.

The Usability and Feasibility of a Dietary Intake Self-Monitoring Application in a Population with Varying Literacy Levels.

Our aim was to study how hemodialysis patients with varying levels of literacy would use a diet and fluid intake monitoring mobile application (DIMA-P) and what would be its impact on their dietary behaviors. We developed a mobile application using user-centered methods and informed by the Integrated Theory of Health Behavior Change (ITHBC). Eight hemodialysis patients were recruited to use the application to record and monitor their diet and fluid intakes for a 6-week study. Overall, the participants had low literacy, numeracy, and technical skills. We collected the data on application usage and administered usability and context-of-use questionnaires to gain insights into the participants' interaction with the application. The participants' portion estimation skills and dietary self-regulation self-efficacy were assessed using various tests. In addition, interdialytic weight gain data were collected to assess the impact of app usage on the participants' health outcomes. The application usage patterns varied, with a general trend towards frequent use (n = 5) correlating with engagement in self-monitoring. The participants gave high comprehensibility, user-friendliness, satisfaction, and usefulness ratings, suggesting that the app was well designed and the target users could easily navigate and interact with the features. While the participants improved in estimating portion sizes, the impact on measuring skills was variable. There was also an improvement in the participants' dietary self-regulation self-efficacy post-study. The interdialytic weight gain trends indicated a slight improvement in fluid and diet management. People with different literacy skills can effectively use icon-based interfaces for portion size estimation and develop personalized usage patterns to self-regulate their fluid and dietary intakes. Moreover, they can experience an enhancement in their dietary self-efficacy skills by using a mobile application aimed at providing nutritional feedback. Furthermore, this research shows that the constructs of the ITHBC are effective in promoting dietary behavior change in a population with varying literacy skills. The target users can benefit from explicitly visualizing the relationship between their health outcomes and the factors influencing those outcomes. These user ambitions could be supported by developing machine learning models. Future research should also focus on enhancing the mechanisms by which technology can further enhance each component of the ITHBC framework.

Development and validation of food frequency questionnaire screener software for sodium intake among palestinian population

BackgroundHigh sodium intake has been linked to negative health effects, including cardiovascular and renal diseases. Traditional dietary sodium assessment methods are time-consuming and subjected to errors. Using technology may increase the efficiency and accuracy of dietary assessment. The objective of this study is to develop and validate a food frequency questionnaire (FFQ) screener using software to assess sodium intake among the Palestinian population. Methodology: The study was conducted in four phases. In Phase 1, Palestinian foods were categorized and subcategorized according to their mode of consumption, sodium content, and food groups. The sodium content values were calculated from Palestinian food composition database. Content validity was done in Phase 2, while in Phase 3, a pilot study was conducted to determine test-retest reliability. In Phase 4, the criterion validity of the screener was assessed by comparing the results of sodium intake from the FFQ screener with the results from a 24-hour urinary sodium test and a 3-day diet recall. Correlations between the sodium intake values from the three methods were analyzed using Pearson correlation tests, and the difference was assessed using the Bland-Altman test.ResultsThe developed FFQ screener sodium screener included 41 food items categorized into nine groups, with photo-based portion size estimation and frequency of consumption. The reliability test showed a Pearson correlation coefficient of 0.7, p < 0.01 using test and retest. For criterion validity, the correlation coefficient between dietary sodium intake using the FFQ screener software and the 24-hour urine sodium test was (0.6, p < 0.000). The correlation coefficient between dietary sodium intake using the FFQ screener software and dietary sodium intake using a 3-day recall was (0.3, p < 0.000). Sodium intake was significantly correlated with preferences for low-sodium food and previous salt reduction, p < 0.05.ConclusionsUsing the FFQ screener software was a valid and reliable method for assessing dietary sodium intake. Using the photo-based method to estimate portion size improved precision and accuracy in diet assessment.

Fruits and vegetables dietary intake and its estimated consumption among adults receiving antiretroviral therapy in health facilities in Northcentral Ethiopia: a multi-facility cross-sectional study.

Despite the significant role of fruit and vegetables (FAVs) in preventing a variety of chronic diseases and their potential to bolster immune responses and slow the progression of HIV infection to AIDS, there is a lack of studies on the dietary intake of FAVs among HIV-infected adults in Africa, including Ethiopia. Hence, this study aimed to investigate the magnitude of FAV intake and estimated consumption among HIV-infected adults receiving antiretroviral therapy (ART) in northcentral Ethiopia. A multifacility cross-sectional study was conducted on the FAV intake among 865 HIV-infected adults receiving ART. A Poisson regression model with robust variance was used to identify factors associated with FAVs dietary intake. The study indicated that 655 (76.34%; 95% CI: 73.38, 79.07) HIV-infected adults reported consuming FAVs less than once per day, with 838 (97.67%, 95% CI: 96.41, 98.49) and 676 (78.79%, 95% CI: 75.92, 81.40) HIV-infected adults reporting consuming fruits and vegetables less than once per day, respectively. The median (IQR) total FAV intake was 271.3 (IQR: 92.5, 439.5) g/day, with the median (IQR) intake of fruits being 248.1 (IQR: 100.0, 400.0) g/day and vegetables being 273.78 (IQR: 82.44, 348.33) g/day, respectively. We found that being divorced (APR = 1.57, 95% CI: 1.16, 2.12), employed as a daily laborer (APR = 2.08, 95% CI: 1.36, 3.20), being employed (APR = 1.77, 95% CI: 1.10, 2.84), merchants (APR = 1.59, 95% CI: 1.03, 2.47), having children as caregivers (APR = 1.61, 95% CI: 1.02, 2.55), an advanced WHO clinical stage (APR = 1.32, 95% CI: 1.32(1.03, 1.69), and receiving ART for more than 8 years (APR = 1.78, 95% CI: 1.18, 2.67) were found to be independent predictors of FAV dietary intake among HIV-infected adults. From the findings, we understood that farmers were less likely to consume FAVs compared to employed individuals, daily laborers, and merchants. The finding indicated a very low level of FAV dietary intake among HIV-infected adults receiving ART, falling well-below the minimum recommendation for physically active adults. Despite living in areas with surplus production and producing these items, farmers are less likely to consume FAV. The study emphasizes the importance of focusing on the early stage of ART treatment for patients and family therapy, including counseling and guidance on consuming healthy diets such as FAVs, to enhance the role of children as caregivers for their families. Additionally, there is a need for comprehensive nutritional counseling to improve FAV consumption, with a particular emphasis on educating individuals about portion size estimation for the consumption of FAVs.

Development and Validation of Photographic Food Atlas: Guidance for Portion Size Estimation, Carbohydrate Counting, and Energy Intake Estimation

Development and Validation of Photographic Food Atlas: Guidance for Portion Size Estimation, Carbohydrate Counting, and Energy Intake Estimation

Do people need guidance to estimate a food portion size? Evidence from an exploratory eye-tracker study

A promising strategy to encourage portion control involves clear guidance and portion information on product packaging alongside nutrition details. However, literature on the impact of this information on serving sizes is conflicting. To gather more objective evidence about how consumers interact with on-pack portion guidance, we conducted a laboratory-based eye-tracker study with 66 participants completing two portion-size estimation tasks. In the first, participants estimated serving sizes indirectly by gauging how many people a product pack could serve. The second task involved direct portion size selection using pictorial representations of the food portion on a virtual plate. Additionally, we explored how participants’ familiarity with products affected their portion estimations. Results: when portion guidance was presented, errors in portion estimation significantly decreased only in the indirect task, where 85% of participants showed an improved accuracy. This suggests that the way individuals are prompted to estimate portion sizes influences their approach and their reliance on the provided guidance. Higher error rates occurred when participants were more familiar with the products. For less familiar products, the lower portion estimation errors were associated with the longer fixations on the portion graphic in the indirect task. In addition, participants who quickly noticed the portion graphic provided more accurate portion size estimates. This emphasizes the practical importance of swiftly locating portion information on-pack to enhance estimation accuracy.

Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis.

Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, prior AI methodologies tackle dietary assessment in a fragmented landscape (e.g., merely recognizing food types or estimating portion size), and encounter challenges in their ability to generalize across a diverse range of food categories, dietary behaviors, and cultural contexts. Recently, the emergence of multimodal foundation models, such as GPT-4V, has exhibited transformative potential across a wide range of tasks (e.g., scene understanding and image captioning) in various research domains. These models have demonstrated remarkable generalist intelligence and accuracy, owing to their large-scale pre-training on broad datasets and substantially scaled model size. In this study, we explore the application of GPT-4V powering multimodal ChatGPT for dietary assessment, along with prompt engineering and passive monitoring techniques. We evaluated the proposed pipeline using a self-collected, semi free-living dietary intake dataset comprising 16 real-life eating episodes, captured through wearable cameras. Our findings reveal that GPT-4V excels in food detection under challenging conditions without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further facilitating the process of dietary assessment.

Starving off death: Mortality salience impacts women’s body image and disordered eating

From a Terror Management perspective, the pursuit of thinness that characterizes eating disorders (EDs) is arguably a culturally endorsed way to mitigate death anxiety. In the present studies, we used the mortality salience (MS) paradigm to examine whether priming death increases ED symptoms. We recruited two samples of women from undergraduate (Study 1, N = 120), and clinically relevant (Study 2, N = 154) populations. After priming, participants completed measures of potential confounds (e.g., neuroticism, affect). Next, we assessed ED attitudes and behavior using a portion size estimation task, and measures of body dissatisfaction and eating intention. Study 1 findings were inconsistent with the claimed role of death anxiety in ED related behavior. However, in Study 2, MS priming led to increased dissatisfaction with current thinness and smaller portion sizes for high-fat compared to low-fat food. Overall, the results suggest that death anxiety may, at least partially, drive ED symptoms.

Estimation accuracy of bean bags as portion size estimation aids for amorphous foods

Objective: A study was undertaken to explore the portion size estimation accuracy of bean bags as low-cost volumetric portion size estimation aids for amorphous foods. Designs: Three observational, cross-sectional and three experimental/quasi-experimental developmental evaluation sub-studies were carried out. Settings: Observational, cross-sectional: one retirement village and four schools. Experimental/quasi-experimental: one South African university. Participants: Observational, cross-sectional: elderly persons, adult women (school educators), schoolchildren. Experimental/quasi-experimental: university students. In total N = 541; > 3 800 observations. Variables measured: Using a standardised set of bean bags (test object; volume range: 60–625 ml), volumes of different amorphous foods (reference objects: actual foods or representations) in varying portion sizes had to be estimated. Accuracy (outcome measure) was perfect if volumes of test and reference object were identical. Acceptable estimation accuracy allowed for misestimation by one bean bag size. Test–retest reproducibility was also assessed. Analysis: Descriptive statistics (proportions perfect and acceptable accuracy). Results: Across the sub-studies, perfect accuracy ranged from 22–65% depending on participants, reference food and portion size. Irrespective thereof, acceptable accuracy was noted in > 70% of observations. Reproducibility varied (range: 28–67% agreement). Conclusions and implications: Perfect portion size estimation of amorphous foods remains challenging. When misestimation by 60–125 ml still serves the purpose of a dietary assessment, bean bags show promise for cost-effective food volume quantification, especially on group level in resource-limited settings.

Adapting Intake24 for Aotearoa - New Zealand

National nutrition surveys play a pivotal role in shaping public health policies and programmes by providing valuable insights into dietary intake and the nutritional wellbeing of a population. A team from the University of Auckland and Massey University worked alongside the Ministry of Health and the Ministry for Primary Industries to develop the methods and tools for a future New Zealand Nutrition Survey. Throughout these developmental stages, we partnered and engaged with Māori as tangata whenua, and other key ethnic groups in Aotearoa - New Zealand, ensuring that their unique dietary practices and preferences were accurately captured. This presentation centres on the adaptation of Intake24, an innovative web-based 24-hour dietary recall tool, to optimize dietary data collection within the New Zealand context. The adaptation process involved several key steps including rationalisation of a New Zealand-specific food list, incorporating cultural dishes, adding new portion size estimation aids, and further customisation of the user interface(1). We provide new insights into the user experience and the tool’s functionality, sharing findings from field testing and valuable user feedback. This approach ensures collection of dietary data that is truly representative of the New Zealand population and acknowledges the rich diversity and dietary nuances within the country. As such, this adapted New Zealand version of Intake24 could serve as an essential tool for use in a future National Nutrition Survey or other research initiatives to collect accurate, culturally sensitive, and actionable nutrition data providing evidence to inform future public health programmes and policies.

Empirically derived portion sizes from the DOrtmund Nutritional and Anthropometric Longitudinally Designed (DONALD) study for 4- to 18-year-old children and adolescents to simplify analysis of dietary data using FFQ.

To apply FFQ, knowledge about portion sizes is relevant. According to increased energy and nutrient requirements, average portion sizes of foods are supposed to increase during growth. We provide empirically derived portion sizes for 4- to 18-year-olds in different age groups to facilitate analyses of FFQ data in children and adolescents. Using data from the dynamic DOrtmund Nutritional and Anthropometric Longitudinally Designed cohort study, quantile regression for smoothing percentiles was used to derive portion sizes as a function of age from which age- and food group-specific portion sizes were calculated as median food group intake (g). Dortmund, Germany. Data from 3-day weighed dietary records (WDR) of 1,325 participants (♀: 653) were analysed. Participants provided in total 9,828 WDR (on average 7·5 per participant) between 1985 and 2022. WDR were grouped into five age groups, whereby each age group covered 3 years of age. In total, 11 955 food items were reported and categorised into sixteen major food groups with seventy-one sub-groups. Portion sizes tended to increase with age, except for milk- and plant-based alternatives. Comparing 4- to 6-year-olds to 16- to 18-year-olds, portion size increased between 22·2 % (processed meat: 18 g v. 22 g) and 173·3 % (savoury snacks: 15 g v. 41 g). We provide empirically derived portion sizes for children and adolescents. These data are useful to establish dietary assessment methods based on estimates of portion sizes, such as FFQ, for children and adolescents.

Development and evaluation of food photograph series software for portion size estimation among urban North Indian adults

BACKGROUND: Accurate population specific aids are needed for food portion size estimation in diet assessment. OBJECTIVE: To develop and evaluate a food photograph series software for accurate portion size estimation among urban North Indian adults. METHODS: A preliminary food consumption survey was conducted on 60 adults (25–60 years, male = female = 30) selected purposively from urban Delhi. A range of portion sizes of commonly consumed food items were standardized and photographed at 45 degree angle. An online portion size estimation tool was developed comprising data on 368 recipes and photographs for 313 food items. Real time (part A) and recalled estimation after 24 hours (part B) was done for pre-weighed food portions by participants (n = 30, 25–60 years, male = female = 15) using the software. RESULTS: The % mean relative error in estimation of 24 pre-weighed food portions was –5±22.61% and 13.07±53.22% for parts A and B respectively. Significant correlation between actual and estimated food portions was observed (r &gt; 0.90, p &lt; 0.0001). Correct picture was selected by participants in≥60% estimations while correct or adjacent picture was selected in≥89% estimations. CONCLUSIONS: The software is a useful aid for dietitians and other nutrition professionals for accurate portion size estimation among urban North Indian adults.

Estimation of food portion sizes in women of childbearing age and young children in Ouagadougou (Burkina Faso) using a food photography atlas and salted replicas: Comparison with weighed records.

Quantitative assessment of foods consumed when using 24-hour dietary recall requires accurate tools to estimate portion sizes. Therefore, we developed a food portion photography atlas with age-appropriate portion sizes for 11 foods frequently consumed by young children (sizes for 6-11-month- and for 12-23-month-old children) and women of childbearing age in Ouagadougou, Burkina Faso capital. We then compared the accuracy and precision of portion estimation with this atlas and with salted replicas relative to weighed records (the reference). After weighing, we randomly assigned food portions to 67 women and their children. The next day, women estimated the served portions and leftovers by recall using the atlas and then salted replicas (n = 1156 measurements, ranging from 19 to 113 for each food). For most food types, the portions estimated with the atlas and salted replicas were positively correlated and showed good concordance with the weighed records. However, accuracy and precision varied in function of the estimation method, food type, and age group. The mean crude differences ranged from -28 to +12g (with errors in absolute values from 24 to 69%) for children, and from -32 to +44g (errors from 17 to 56%) for women. The atlas-based method showed the lowest Lin's concordances (coefficients of 0.1 to 0.2) for the leafy vegetable dish, meat, and fish in 12-23-month-old children. Bland-Altman plots indicated that the salted replicas allowed estimating the consumed portions with fewer errors than the photographic atlas (56 to 91% vs 46 to 79% between the limits of ±50%). Our study highlights that mothers have difficulties in perceiving the quantities of food consumed by their children. Our findings also indicate that the food atlas could be used in food consumption surveys when salted replicas are not available for all food types.

PTFS06-05-23 Portion Size Estimation of Food in a Bowl From Images

PTFS06-05-23 Portion Size Estimation of Food in a Bowl From Images

Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana

BackgroundImportant gaps exist in the dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion-size estimation. Dietary assessment tools leveraging mobile technologies exist but only a few have been validated in LMICs. ObjectiveWe validated Food Recognition Assistance and Nudging Insights (FRANI), a mobile artificial intelligence (AI) dietary assessment application in adolescent females aged 12–18 y (n = 36) in Ghana, against weighed records (WR), and multipass 24-hour recalls (24HR). MethodsDietary intake was assessed during 3 nonconsecutive days using FRANI, WRs, and 24HRs. Equivalence of nutrient intake was tested using mixed-effect models adjusted for repeated measures, by comparing ratios (FRANI/WR and 24HR/WR) with equivalence margins at 10%, 15%, and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC). ResultsEquivalence for FRANI and WR was determined at the 10% bound for energy intake, 15% for 5 nutrients (iron, zinc, folate, niacin, and vitamin B6), and 20% for protein, calcium, riboflavin, and thiamine intakes. Comparisons between 24HR and WR estimated equivalence at the 20% bound for energy, carbohydrate, fiber, calcium, thiamine, and vitamin A intakes. The CCCs by nutrient between FRANI and WR ranged between 0.30 and 0.68, which was similar for CCC between 24HR and WR (ranging between 0.38 and 0.67). Comparisons of food consumption episodes from FRANI and WR found 31% omission and 16% intrusion errors. Omission and intrusion errors were lower when comparing 24HR with WR (21% and 13%, respectively). ConclusionsFRANI AI–assisted dietary assessment could accurately estimate nutrient intake in adolescent females compared with WR in urban Ghana. FRANI estimates were at least as accurate as those provided through 24HR. Further improvements in food recognition and portion estimation in FRANI could reduce errors and improve overall nutrient intake estimations.

Relative Validity and Reliability of the Remind App as an Image-Based Method to Assess Dietary Intake and Meal Timing in Young Adults.

Image-based dietary records have been validated as tools to evaluate dietary intake. However, to determine meal timing, previous studies have relied primarily on image-based smartphone applications without validation. Noteworthy, the validation process is necessary to determine how accurately a test method measures meal timing compared with a reference method over the same time period. Thus, we aimed to assess the relative validity and reliability of the Remind® app as an image-based method to assess dietary intake and meal timing. For this purpose, 71 young adults (aged 20-33 years, 81.7% women) were recruited for a 3-day cross-sectional study, where they completed a 3-day image-based record using the Remind app (test method) and a 3-day handwritten food record (reference method). The relative validity of the test method versus the reference method was assessed using multiple tests including Bland-Altman, % difference, paired t-test/Wilcoxon signed-rank test, Pearson/Spearman correlation coefficients, and cross-classification. We also evaluated the reliability of the test method using an intra-class correlation (ICC) coefficient. The results showed that, compared to the reference method, the relative validity of the test method was good for assessing energy and macronutrient intake, as well as meal timing. Meanwhile, the relative validity of the test method to assess micronutrient intake was poor (p < 0.05) for some micronutrients (iron, phosphorus, potassium, zinc, vitamins B1, B2, B3, B6, C, and E, and folates) and some food groups (cereals and grains, legumes, tubers, oils, and fats). Regarding the reliability of an image-based method to assess dietary intake and meal timing, results ranged from moderate to excellent (ICC 95% confidence interval [95% CI]: 0.50-1.00) for all nutrients, food groups (except oils and fats, which had low to moderate reliability), and meal timings. Thus, the results obtained in this study provide evidence of the relative validity and reliability of image-based methods to assess dietary intake (energy, macronutrients, and most food groups) and meal timing. These results open up a new framework for chrononutrition, as these methods improve the quality of the data collected and also reduce the burden on users to accurately estimate portion size and the timing of meals.

Estimation of Plate and Bowl Dimensions for Food Portion Size Assessment in a Wearable Sensor System.

Automatic food portion size estimation (FPSE) with minimal user burden is a challenging task. Most of the existing FPSE methods use fiducial markers and/or virtual models as dimensional references. An alternative approach is to estimate the dimensions of the eating containers prior to estimating the portion size. In this article, we propose a wearable sensor system (the automatic ingestion monitor integrated with a ranging sensor) and a related method for the estimation of dimensions of plates and bowls. The contributions of this study are: 1) the model eliminates the need for fiducial markers; 2) the camera system [automatic ingestion monitor version 2 (AIM-2)] is not restricted in terms of positioning relative to the food item; 3) our model accounts for radial lens distortion caused due to lens aberrations; 4) a ranging sensor directly gives the distance between the sensor and the eating surface; 5) the model is not restricted to circular plates; and 6) the proposed system implements a passive method that can be used for assessment of container dimensions with minimum user interaction. The error rates (mean ± std. dev) for dimension estimation were 2.01% ± 4.10% for plate widths/diameters, 2.75% ± 38.11% for bowl heights, and 4.58% ± 6.78% for bowl diameters.

Dietary Habits of Children 0 - 23 Months in Rural Kansas: Early Life Diets of Rural Children.

Children in rural areas face increased rates of obesity compared to their urban counterparts, and diet in early childhood may influence the development of diseases related to food intake. This study sought to determine current diet of children 0-23 months of age in rural Kansas. Medical students participating in 6-week, summer, rural clinical experiences offered the survey to caregivers of children 0-23 months, born at term as singletons without a specialized diet. The survey asked respondents to answer with the child's diet over the last seven days. The survey was in the style of a validated Food Frequency Questionnaire for infants with an image for estimating portion sizes. Diets were compared to guidelines set by the Dietary Guidelines for Americans, 2020-2025. Of 44 responses, 21 children were aged 0-5 months, 7 aged 6-11 months, and 16 aged 12-23 months. Breastfeeding rates were nearly double reported national averages. All children aged 0-5 months met guidelines. None of the children 6-11 months or 12-23 months met guidelines. In the 6-11 month group, four consumed food in addition to breastmilk or formula (complementary foods). In the 12-23 month group, protein and dairy foods were lower than, and whole grains and vegetables were higher than, reported national averages, respectively. Children may fall short of meeting dietary recommendations due to foods consumed in addition to breastmilk. There is a need for improved survey methods to capture the diets of young children in the rural United States.

Development and validation of a photographic food atlas of Middle Eastern Mediterranean diet: Toward improved understanding of traditional healthy and sustainable diets.

Middle Eastern Mediterranean diet (MEMD) is a traditional plant-based diet that is commonly consumed and increasingly popular, but not well studied in nutrition research. To facilitate the dietary assessment of MEMD, we developed and validated a photographic food atlas depicting a variety of foods and dishes consumed in the MEM region. The photographic food atlas included 1,002 photos of 400 types of foods and traditional dishes photographed characterizing MEMD. Foods and dishes were prepared by a professional cook and were subsequently photographed as a series of photos depicting portion size options. In a validation study, 45 individuals aged 20-50 years were recruited to assess portion size estimation of 25 representative food-photo series for each item. The validity of portion size estimation was assessed by comparing actual and reported estimates using Pearson or Spearman correlation tests. Sizes of the differences between estimated portions and the actual served portion sizes were calculate as mean differences and standard deviations. In the validation study, there was a strong correlation (r > 0.7) between estimated portion size of actual foods for 7 food items, such as pita bread, milk, labneh, and tomatoes, a moderate correlation (< 0.5 | r | < 0.7) for 12 items, such as meat, chicken, and grapes, and weak correlation (r < 0.3) for 6 items, such as seeds. Underestimation of portion sizes was more commonly observed for food items quantified when using "grams" or "milliliters" as a unit of measurement. In contrast, when household measurements were used, the participants tended to overestimate the portion sizes of respective foods and dishes. We developed and validated a photographic food atlas depicting a wide variety of foods and dishes typical for the MEMD. The application of the photographic food atlas may facilitate the accurate assessment of adherence to MEMD and support the understanding of its health and sustainability aspects. Further methodological work is warranted to extend the list of food items and to evaluate the validity of the food atlas among larger and more heterogeneous groups of participants.

Food Image Segmentation Using Multi-Modal Imaging Sensors with Color and Thermal Data

Sensor-based food intake monitoring has become one of the fastest-growing fields in dietary assessment. Researchers are exploring imaging-sensor-based food detection, food recognition, and food portion size estimation. A major problem that is still being tackled in this field is the segmentation of regions of food when multiple food items are present, mainly when similar-looking foods (similar in color and/or texture) are present. Food image segmentation is a relatively under-explored area compared with other fields. This paper proposes a novel approach to food imaging consisting of two imaging sensors: color (Red-Green-Blue) and thermal. Furthermore, we propose a multi-modal four-Dimensional (RGB-T) image segmentation using a k-means clustering algorithm to segment regions of similar-looking food items in multiple combinations of hot, cold, and warm (at room temperature) foods. Six food combinations of two food items each were used to capture RGB and thermal image data. RGB and thermal data were superimposed to form a combined RGB-T image and three sets of data (RGB, thermal, and RGB-T) were tested. A bootstrapped optimization of within-cluster sum of squares (WSS) was employed to determine the optimal number of clusters for each case. The combined RGB-T data achieved better results compared with RGB and thermal data, used individually. The mean ± standard deviation (std. dev.) of the F1 score for RGB-T data was 0.87 ± 0.1 compared with 0.66 ± 0.13 and 0.64 ± 0.39, for RGB and Thermal data, respectively.