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 Experiment Video

Updated: Jan 11, 2026

Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

18.0K

Enhanced Fetal Plane Classification in Ultrasound Imaging via Prototypical Networks and Few-Shot Learning.

Mahamoud Abdi Abdillahi1, Mohammed Rashad Baker2, Ayşe Doğru3

  • 1Department of Electronics and Computer Engineering, Çankırı Karatekin University, 18100, Çankırı, Turkey.

Journal of Imaging Informatics in Medicine
|November 18, 2025
PubMed
Summary

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

A hybrid super ensemble learning model for the early-stage prediction of diabetes risk.

Medical & biological engineering & computing·2023
Same author

A novel color labeled student modeling approach using e-learning activities for data mining.

Universal access in the information society·2022
Same author

Implementing Critical Machine Learning (ML) Approaches for Generating Robust Discriminative Neuroimaging Representations Using Structural Equation Model (SEM).

Computational and mathematical methods in medicine·2022
Same author

Correlation value determined to increase Salmonella prediction success of deep neural network for agricultural waters.

Environmental monitoring and assessment·2022

A new few-shot learning framework (FSL-VGG19) significantly improves automated fetal ultrasound image classification. It achieves high accuracy with limited data, outperforming traditional convolutional neural networks (CNNs).

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Automated classification of standard fetal-plane ultrasound images is crucial for prenatal diagnosis.
  • Challenges include limited labeled data and imbalanced class distributions, hindering traditional deep learning models.
  • Existing convolutional neural networks (CNNs) struggle with data scarcity in this domain.

Purpose of the Study:

  • To develop and evaluate a data-efficient framework for few-shot learning in fetal ultrasound image classification.
  • To compare the performance of the proposed framework against established CNN baselines.
  • To assess the impact of data availability (K-shot size) on classification accuracy.

Main Methods:

  • Proposed a framework combining a prototypical network with a VGG19 feature extractor (FSL-VGG19) for few-shot learning.
Keywords:
Deep learningFetal ultrasoundFew-shot learningImage classificationPrototypical networksVGG19

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

727

Related Experiment Videos

Last Updated: Jan 11, 2026

Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

18.0K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

727
  • Compared FSL-VGG19 against MobileNetV2, ResNet50, VGG16, and VGG19 on three public fetal ultrasound datasets.
  • Utilized five-fold cross-validation for model selection and employed Friedman and Nemenyi tests for statistical significance.

    • Main Results:

    • FSL-VGG19 achieved high accuracies: 96.88% (Maternal-Fetal), 97.80% (FPSU 23), and 94.38% (Africa).
    • The proposed framework significantly outperformed all CNN baselines by 1.1-24.4 percentage points (p < 0.05).
    • Sensitivity analysis revealed a positive correlation between K-shot size and accuracy, with a 30.9% difference between one-shot and ten-shot learning.

    Conclusions:

    • The FSL-VGG19 framework offers a robust and generalizable solution for fetal-plane classification, minimizing annotation bottlenecks and class imbalance.
    • This data-efficient approach is particularly valuable for resource-poor clinical settings.
    • The study demonstrates the effectiveness of few-shot learning in improving automated analysis of medical images with limited data.