Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Using a Fine-Tuned Commercial Artificial Intelligence Model to Assess Nutrients from Photographs of Japanese Meals.

Journal of diabetes science and technology·2026
Same author

Digital Intervention Increasing Sleep Duration Among People With Type 2 Diabetes: Pilot Randomized Controlled Trial.

Journal of diabetes science and technology·2026
Same author

Research Code Sharing in Support of Gold Standard Science.

Journal of diabetes science and technology·2026
Same author

Efficacy of FiberMore, an AI-Based mHealth Intervention to Increase Dietary Fiber Intake Among Type 2 Diabetes Patients: Protocol for a Pilot Randomized Controlled Trial.

JMIR research protocols·2025
Same author

Dietary Fiber Estimate of DialBetesPlus App Users: Secondary Analysis of Data From a Randomized Controlled Trial.

JMIR formative research·2025
Same author

Enhancing Antidiabetic Drug Selection Using Transformers: Machine-Learning Model Development.

JMIR medical informatics·2025

Related Experiment Video

Updated: Dec 3, 2025

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

6.1K

Machine Learning-Based Screening of Healthy Meals From Image Analysis: System Development and Pilot Study.

Kyoko Sudo1, Kazuhiko Murasaki2, Tetsuya Kinebuchi2

  • 1Department of Information Sciences, Toho University, Chiba, Japan.

JMIR Formative Research
|October 26, 2020
PubMed
Summary

This study introduces a novel algorithm for estimating meal healthiness from images, simplifying dietary control for individuals managing diabetes or on diets. The system accurately ranks meals, aiding healthcare professionals in creating healthier meal plans.

Keywords:
deep neural networkdiethealthinessmeal imagesmedical informaticsneural networknutrition

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq
04:54

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Published on: March 19, 2021

5.0K

Related Experiment Videos

Last Updated: Dec 3, 2025

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

6.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq
04:54

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Published on: March 19, 2021

5.0K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Nutritional Science

Background:

  • Existing health monitoring systems often require manual input and lack user motivation.
  • Current nutrition estimation systems provide detailed values but lack a holistic healthiness standard.
  • Effective dietary control necessitates continuous monitoring and user engagement.

Purpose of the Study:

  • To introduce 'healthiness of meals' as a meaningful standard for dietary assessment.
  • To develop a novel algorithm for estimating meal healthiness directly from images without manual input.

Main Methods:

  • A deep neural network was employed to extract features from meal images.
  • A ranking network was trained using a dataset ranked by a human dietary expert.
  • The system was validated by comparing its healthiness ranking with a dietitian's judgment.

Main Results:

  • The algorithm achieved a high correlation (0.72) with a dietitian's healthiness ranking.
  • Pretraining on a large public meal dataset improved performance, overcoming data limitations.
  • The proposed network demonstrated higher accuracy in healthiness estimation than conventional methods.

Conclusions:

  • An image-based system for ranking meal healthiness was successfully developed.
  • The system's ranking correlates well with expert nutritional assessments.
  • This technology can assist healthcare professionals in developing personalized meal plans, particularly for diabetic patients.