Image-assisted Dietary Assessment Research Articles

Image-based volume estimation for food in a bowl

Image-assisted dietary assessment has become popular in dietary monitoring studies in recent years. However, food volume estimation is still a challenging problem due to the lack of 3D information in a 2D image and the occlusion of the food by itself or container (e.g., bowl, cup). This study aims to investigate the relationship between the observable surface of food in a bowl and a normalized index (i.e., bowl fullness) to represent its volume. A mathematical model is established for describing different shapes of bowls, and a convenient experimental method is proposed to determine the bowl shape. An image feature called Food Area Ratio (FAR) is used to estimate the volume of food in a bowl based on the relationship between bowl fullness and the FAR calculated from the image. Both simulations and experiments with real food/liquid demonstrate the feasibility and accuracy of the proposed approach.

A Novel Food Record App for Dietary Assessments Among Older Adults With Type 2 Diabetes: Development and Usability Study.

BackgroundMore than 1 in 4 people in the United States aged 65 years and older have type 2 diabetes. For diabetes care, medical nutrition therapy is recommended as a clinically effective intervention. Previous researchers have developed and validated dietary assessment methods using images of food items to improve the accuracy of self-reporting over traditional methods. Nevertheless, little is known about the usability of image-assisted dietary assessment methods for older adults with diabetes.ObjectiveThe aims of this study were (1) to create a food record app for dietary assessments (FRADA) that would support image-assisted dietary assessments, and (2) to evaluate the usability of FRADA for older adults with diabetes.MethodsFor the development of FRADA, we identified design principles that address the needs of older adults and implemented three fundamental tasks required for image-assisted dietary assessments: capturing, viewing, and transmitting images of food based on the design principles. For the usability assessment of FRADA, older adults aged 65 to 80 years (11 females and 3 males) were assigned to interact with FRADA in a lab-based setting. Participants’ opinions of FRADA and its usability were determined by a follow-up survey and interview. As an evaluation indicator of usability, the responses to the survey, including an after-scenario questionnaire, were analyzed. Qualitative data from the interviews confirmed the responses to the survey.ResultsWe developed a smartphone app that enables older adults with diabetes to capture, view, and transmit images of food items they consumed. The findings of this study showed that FRADA and its instructions for capturing, viewing, and transmitting images of food items were usable for older adults with diabetes. The survey showed that participants found FRADA easy to use and would consider using FRADA daily. The analysis of the qualitative data from interviews revealed multiple categories, such as the usability of FRADA, potential benefits of using FRADA, potential features to be added to FRADA, and concerns of older adults with diabetes regarding interactions with FRADA.ConclusionsThis study demonstrates in a lab-based setting not only the usability of FRADA by older adults with diabetes but also potential opportunities using FRADA in real-world settings. The findings suggest implications for creating a smartphone app for an image-assisted dietary assessment. Future work still remains to evaluate the feasibility and validity of FRADA with multiple stakeholders, including older adults with diabetes and dietitians.

Validating an automated image identification process of a passive image-assisted dietary assessment method: proof of concept.

To validate an automated food image identification system, DietCam, which has not been validated, in identifying foods with different shapes and complexities from passively taken digital images. Participants wore Sony SmartEyeglass that automatically took three images per second, while two meals containing four foods, representing regular- (i.e., cookies) and irregular-shaped (i.e., chips) foods and single (i.e., grapes) and complex (i.e., chicken and rice) foods, were consumed. Non-blurry images from the meals' first 5 min were coded by human raters and compared with DietCam results. Comparisons produced four outcomes: true positive (rater/DietCam reports yes for food), false positive (rater reports no food; DietCam reports food), true negative (rater/DietCam reports no food) or false negative (rater reports food; DietCam reports no food). Laboratory meal. Thirty men and women (25·1 ± 6·6 years, 22·7 ± 1·6 kg/m2, 46·7 % White). Identification accuracy was 81·2 and 79·7 % in meals A and B, respectively (food and non-food images) and 78·7 and 77·5 % in meals A and B, respectively (food images only). For food images only, no effect of food shape or complexity was found. When different types of images, such as 100 % food in the image and on the plate, <100 % food in the image and on the plate and food not on the plate, were analysed separately, images with food on the plate had a slightly higher accuracy. DietCam shows promise in automated food image identification, and DietCam is most accurate when images show food on the plate.

Validating an Automated Food Image Identification System of a Passive Image-Assisted Dietary Assessment Method

Validating an Automated Food Image Identification System of a Passive Image-Assisted Dietary Assessment Method

Comparison of nutrient intakes in South Asians with type 2 diabetes mellitus and controls living in the United States

AimsDespite having a high risk for type 2 diabetes mellitus (T2DM), little is known about the relationship between nutrient intakes and T2DM in South Asians (SA) in the U.S. In addition, the available data are limited to a few macronutrients and collected using subjective measures. Therefore, we compared macro- and micro-nutrient intakes of SA migrants with and without T2DM using an objective measure. MethodsSA in the U.S. with T2DM (n = 44) and controls (n = 33) reported their dietary intake using image-assisted dietary assessment method. They took pictures of all foods/drinks consumed on two weekdays and one weekend day. Age, gender distribution, and body mass index were similar across the two groups. ResultsSA with T2DM, as compared to controls, consumed less total energy (mean difference: 499 kcal/d; p < .0001), linoleic acid (3.6 g/d; p = .003), dietary fiber (8.6 g/d; p < .0001), vitamin A (262 µg/d; p = .003), vitamin E (2.7 mg/d; p = .007), calcium (133 mg/d; p = .01), magnesium (116 mg/d; p < .0001), zinc (1.4 mg/d; p = .004), potassium (754 mg/d; p < .0001), and β-carotene (1761 µg/d; p = .03). SA with T2DM, as compared to controls, were significantly more likely not to meet the requirements for linoleic acid, dietary fiber, vitamin E, calcium, magnesium, zinc, and potassium (p < .05). ConclusionsSA with T2DM, compared to controls, consume less total energy and have lower consumption of many nutrients associated with reduced risk of T2DM. Dietary interventions to reduce risk for T2DM are warranted in SA.

Validity and practicability of smartphone-based photographic food records for estimating energy and nutrient intake.

Image-assisted dietary assessment methods are frequently used to record individual eating habits. This study tested the validity of a smartphone-based photographic food recording approach by comparing the results obtained with those of a weighed food record. We also assessed the practicality of the method by using it to measure the energy and nutrient intake of college students. The experiment was implemented in two phases, each lasting 2 weeks. In the first phase, a labelled menu and a photograph database were constructed. The energy and nutrient content of 31 randomly selected dishes in three different portion sizes were then estimated by the photograph-based method and compared with a weighed food record. In the second phase, we combined the smartphone-based photographic method with the WeChat smartphone application and applied this to 120 randomly selected participants to record their energy and nutrient intake. The Pearson correlation coefficients for energy, protein, fat, and carbohydrate content between the weighed and the photographic food record were 0.997, 0.936, 0.996, and 0.999, respectively. Bland-Altman plots showed good agreement between the two methods. The estimated protein, fat, and carbohydrate intake by participants was in accordance with values in the Chinese Residents' Nutrition and Chronic Disease report (2015). Participants expressed satisfaction with the new approach and the compliance rate was 97.5%. The smartphone-based photographic dietary assessment method combined with the WeChat instant messaging application was effective and practical for use by young people.

Dietary under-reporting: what foods and which meals are typically under-reported?

Little objective information exists regarding which foods and meals are typically under-reported during retrospective self-reported dietary assessments. Automated wearable cameras record dietary behaviours in free-living settings and allow the context of under-reporting to be explored. As part of a study to validate image-assisted dietary assessment, 40 participants wore a wearable camera on days before three image-assisted 24-h dietary recalls. The foods and meals were typically under-reported, and the environmental and social contexts of under-reporting were assessed. Under-reporting occurred most frequently during afternoon snacks (75/265 foods), dinner (54/265 foods) and breakfast (44/265 foods). Snack foods were most frequently unreported during afternoon snacks, and condiments were most frequently under-reported at breakfasts. No clear pattern of social or environmental contexts for under-reporting was observed. Wearable cameras can identify when specific foods are likely to be under-reported during retrospective dietary assessments. Problematic foods and meals identified could be given additional attention during dietary assessments.

Image-Assisted Dietary Assessment: A Systematic Review of the Evidence

Images captured during eating episodes provide objective information to assist in the assessment of dietary intake. Images are captured using handheld devices or wearable cameras, and can support traditional self-report or provide the primary record of dietary intake. A diverse range of image-assisted methods have been developed and evaluated but have not been previously examined together. Therefore, a review was undertaken to examine all studies that have evaluated or validated image-assisted methods of dietary assessment for assessing dietary energy intake. Identified image-assisted methods that employ similar methodologies were grouped for comparison. English-language full-text research articles published between January 1998 and November 2013 were searched using five electronic databases. A search of reference lists and associated websites was also conducted. Thirteen studies that evaluated 10 unique image-assisted methods among adults aged 18 to 70 years were included. Ten studies used handheld devices and three studies used wearable cameras. Eight studies evaluated image-based food records, two studies explored the use of images to enhance written food records, and three studies evaluated image-assisted 24-hour dietary recalls. Results indicate images enhance self-report by revealing unreported foods and identify misreporting errors not captured by traditional methods alone. Moreover, when used as the primary record of dietary intake, images can provide valid estimates of energy intake. However, image-assisted methods that rely on image analysis can be prone to underestimation if users do not capture images of satisfactory quality before all foods are consumed. Further validation studies using criterion measures are warranted. The validity among children, adolescents, and elderly persons as well as the feasibility of using image-assisted methods in large samples needs to be examined. Additional research is also needed to better understand the potential applications and pitfalls of wearable cameras.