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

In vivo dedifferentiation of human epidermal cells.

Cell biology international·2007
Same author

What is in a word? No versus Yes differentially engage the lateral orbitofrontal cortex.

Emotion (Washington, D.C.)·2007
Same author

[Gene expression profile changes in oral verrucous carcinoma and oral squamous cell carcinoma].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2007
Same author

Morphology of critical nuclei in solid-state phase transformations.

Physical review letters·2007
Same author

Enhanced cooperative activation effect in the hydrolytic kinetic resolution of epoxides on [Co(salen)] catalysts confined in nanocages.

Angewandte Chemie (International ed. in English)·2007
Same author

[Construction of the three-dimensional finite element model of micro -implant -maxilla].

Hua xi kou qiang yi xue za zhi = Huaxi kouqiang yixue zazhi = West China journal of stomatology·2007

Related Experiment Video

Updated: Oct 2, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Uncertainty-Guided Voxel-Level Supervised Contrastive Learning for Semi-Supervised Medical Image Segmentation.

Yu Hua1, Xin Shu1, Zizhou Wang1

  • 1College of Computer Science, Sichuan University, Section 4, Southern 1st Ring Rd, Chengdu, Sichuan 610065, P. R. China.

International Journal of Neural Systems
|February 28, 2022
PubMed
Summary

This study introduces a novel semi-supervised learning method for medical image segmentation, improving data utilization and reducing overfitting. The approach enhances feature representation and achieves superior performance compared to existing methods.

Keywords:
Supervised contrastive learningmedical image segmentationsemi-supervised learning

More Related Videos

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.9K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K

Related Experiment Videos

Last Updated: Oct 2, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.9K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K

Area of Science:

  • Medical Image Analysis
  • Machine Learning
  • Computer Vision

Background:

  • Semi-supervised learning (SSL) is crucial for medical image segmentation, leveraging limited annotated data with abundant unlabeled data to reduce overfitting.
  • Conventional SSL methods often misuse and underutilize data, leading to model deviation and differential treatment of data types.
  • Existing approaches fail to fully exploit inter-data information, hindering the performance of semi-supervised models.

Purpose of the Study:

  • To propose an advanced semi-supervised method that effectively utilizes unlabeled data to bridge the performance gap between semi-supervised and fully-supervised models in medical image segmentation.
  • To address the data misuse and underutilization issues prevalent in current semi-supervised frameworks.
  • To enhance feature representation learning for improved segmentation accuracy.

Main Methods:

  • The proposed method builds upon the mean-teacher framework, incorporating an improved uncertainty estimation module for consistency constraints and feature vector selection.
  • A novel voxel-level supervised contrastive learning module is introduced to establish dense contrastive relationships between feature vectors from both labeled and unlabeled data.
  • This supervised contrastive approach ensures accurate knowledge learning and extracts maximal information from unlabeled data.

Main Results:

  • The developed method effectively overcomes data misuse and underutilization in semi-supervised learning.
  • It promotes feature representations with enhanced intra-class compactness and inter-class separability, leading to improved performance.
  • Experiments on the Atrial Segmentation Challenge left atrium dataset show superior results compared to state-of-the-art methods.

Conclusions:

  • The proposed semi-supervised method significantly advances medical image segmentation by optimizing the use of unlabeled data.
  • The integration of supervised contrastive learning and uncertainty estimation leads to more robust and accurate segmentation models.
  • This work offers a promising direction for improving the efficiency and effectiveness of semi-supervised learning in medical imaging applications.