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

Causes of congenital heart disease: an integrative narrative review.

Heart (British Cardiac Society)·2026
Same author

A Systematic Review of Heat Exposure on Fetal Heart Rate: More Evidence is Urgently Needed.

American journal of obstetrics & gynecology MFM·2026
Same author

Human-AI Collaboration in Healthcare: A Scoping Review.

NPJ digital medicine·2026
Same author

Prevention of postpartum haemorrhage: from evidence to implementation at scale.

Lancet (London, England)·2026
Same author

Fetal monitoring for high-risk pregnancies using a wearable ultrasound patch.

Nature biotechnology·2026
Same author

Including pregnant and breastfeeding women in clinical trials.

BMJ (Clinical research ed.)·2026

Related Experiment Video

Updated: Oct 21, 2025

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

718

First Trimester Gaze Pattern Estimation Using Stochastic Augmentation Policy Search for Single Frame Saliency

Elizaveta Savochkina1, Lok Hin Lee1, Lior Drukker2

  • 1Department of Engineering Science, University of Oxford, Oxford, UK.

Medical Image Understanding and Analysis : 25Th Annual Conference, MIUA 2021, Oxford, United Kingdom, July 12-14, 2021, Proceedings. Medical Image Understanding and Analysis (Conference) (25Th : 2021 : Online)
|September 3, 2021
PubMed
Summary

Predicting sonographer gaze in ultrasound (US) videos aids analysis of fetal scans. This study uses gaze-tracking data with deep learning and automated data augmentation to improve first-trimester ultrasound image interpretation.

Keywords:
Data augmentationFetal ultrasoundFirst trimesterGaze trackingSingle frame saliency predictionU-Net

More Related Videos

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.1K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

608

Related Experiment Videos

Last Updated: Oct 21, 2025

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

718
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.1K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

608

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Sonographers' gaze during ultrasound (US) scans identifies critical regions for accurate image acquisition and interpretation.
  • Predicting sonographer gaze can reveal spatio-temporal patterns crucial for effective US scanning.

Purpose of the Study:

  • To investigate the utility of sonographer gaze-tracking data within a multimodal deep learning framework.
  • To enhance the analysis of first-trimester fetal ultrasound scans by predicting sonographer visual attention.

Main Methods:

  • Developed an encoder-decoder convolutional neural network with skip connections to predict gaze for each video frame.
  • Utilized a dataset of 115 first-trimester ultrasound videos (29,250 training, 7,290 validation, 9,126 testing frames).
  • Employed automated data augmentation via stochastic policy search to improve model performance and generalization.

Main Results:

  • Automated data augmentation mitigated model overfitting and reduced anatomical view imbalances between training and testing datasets.
  • The proposed model, using learned augmentation policies, outperformed baseline metrics (KLD, SIM, NSS, CC).
  • Specific performance improvements were noted: KLD (2.16 vs 3.17), SIM (0.27 vs 0.21), NSS (4.34 vs 2.92), and CC (0.39 vs 0.28).

Conclusions:

  • Sonographer gaze prediction using deep learning offers a valuable tool for analyzing fetal ultrasound scans.
  • Automated data augmentation is beneficial for improving model robustness and performance on ultrasound datasets of this size.
  • The findings suggest potential for gaze-tracking data to assist in US scanning interpretation and training.