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

Sleep and temperature data from wearable devices support noninvasive detection of diabetes mellitus in a large-scale, retrospective analysis.

Communications medicine·2026
Same author

Testing the Impact of Intensive, Longitudinal Sampling on Assessments of Statistical Power and Effect Size Within a Heterogeneous Human Population: Natural Experiment Using Change in Heart Rate on Weekends as a Surrogate Intervention.

Journal of medical Internet research·2025
Same author

Demographic bias of expert-level vision-language foundation models in medical imaging.

Science advances·2025
Same author

Five million nights: temporal dynamics in human sleep phenotypes.

NPJ digital medicine·2024
Same author

LEAARC Association News: The Vital Role of Lactation Education in Maternal and Infant Health.

Journal of human lactation : official journal of International Lactation Consultant Association·2024
Same author

LEAARC NEWS BRIEF: Lactation Education and Approval Review Committee News.

Journal of human lactation : official journal of International Lactation Consultant Association·2023

Related Experiment Video

Updated: Jun 23, 2025

A Common Marmoset Model of Mother-Infant Intervention for Breastfeeding Disorders in the Presence of Paternal Inhibition and Maternal Neglect
05:04

A Common Marmoset Model of Mother-Infant Intervention for Breastfeeding Disorders in the Presence of Paternal Inhibition and Maternal Neglect

Published on: September 22, 2023

423

Augmenting Telepostpartum Care With Vision-Based Detection of Breastfeeding-Related Conditions: Algorithm Development

Jessica De Souza1, Varun Kumar Viswanath1, Jessica Maria Echterhoff2

  • 1Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, United States.

JMIR AI
|June 24, 2024
PubMed
Summary
This summary is machine-generated.

This study shows that artificial intelligence can accurately detect breastfeeding problems from breast images, helping lactation consultants (LCs) provide faster support. This AI tool can improve care for mothers and reduce LC workload.

Keywords:
AI for health careartificial intelligencebreastfeedingdeep learningdetection modelimage analysismobile phoneperinatal healthremote consultationstelehealthwomen’s health

More Related Videos

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
05:10

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

2.7K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.4K

Related Experiment Videos

Last Updated: Jun 23, 2025

A Common Marmoset Model of Mother-Infant Intervention for Breastfeeding Disorders in the Presence of Paternal Inhibition and Maternal Neglect
05:04

A Common Marmoset Model of Mother-Infant Intervention for Breastfeeding Disorders in the Presence of Paternal Inhibition and Maternal Neglect

Published on: September 22, 2023

423
Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
05:10

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

2.7K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.4K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Breastfeeding support technologies

Background:

  • Breastfeeding is crucial for maternal and infant health, but many mothers discontinue due to issues like nipple damage and mastitis.
  • Lactation consultants (LCs) provide vital support, but face burnout due to high demand and limited resources.
  • Telehealth and image-based support exist, but scalability remains a challenge.

Purpose of the Study:

  • To evaluate the effectiveness of five distinct convolutional neural networks (CNNs) in identifying healthy lactating breasts and six common breastfeeding complications.
  • To assess the potential of these AI models as an auxiliary tool for LCs to expedite triage and patient management.
  • To enhance the overall care experience for breastfeeding mothers through rapid, AI-assisted condition detection.

Main Methods:

  • Utilized five CNN models (Resnet50, VGG16, InceptionV3, EfficientNetV2, DenseNet169) to classify 1078 breast and nipple images.
  • Images were categorized into seven classes: healthy, abscess, mastitis, nipple blebs, dermatosis, engorgement, and nipple damage.
  • Evaluated model performance for both multiclass and binary (healthy vs. unhealthy) classification, including analysis of classification challenges.

Main Results:

  • The best-performing model achieved an average area under the receiver operating characteristic curve (AUC) of 0.93 for multiclass classification and 0.96 for binary classification after data augmentation.
  • Identified image characteristics like overlapping conditions and partial views as factors influencing misclassification.
  • Demonstrated high accuracy in distinguishing between healthy and unhealthy breastfeeding-related conditions.

Conclusions:

  • A vision-based automated detection technique using CNNs shows promise for improving postpartum care.
  • This AI approach can potentially alleviate the workload of LCs by enabling faster decision-making.
  • The technology offers a scalable solution to enhance support for breastfeeding mothers.