Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 12, 2026

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

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

Published on: November 30, 2022

Two-level semi-supervised collaborative medical image segmentation with bidirectional knowledge exchange.

Zhongda Zhao¹, Haiyan Wang², Tao Lei³

¹Key Laboratory of Ocean Acoustics and Sensing Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, 710072, Shaanxi, China.

Medical Image Analysis

|November 5, 2025

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

Detection of thiocyanate through limiting growth of AuNPs with C-dots acting as reductant.

The Analyst·2015

Same author

Combined autotrophic nitritation and bioelectrochemical-sulfur denitrification for treatment of ammonium rich wastewater with low C/N ratio.

Environmental science and pollution research international·2015

Same author

Perpendicular Exchange-Biased Magnetotransport at the Vertical Heterointerfaces in La(0.7)Sr(0.3)MnO3:NiO Nanocomposites.

ACS applied materials & interfaces·2015

Same author

CO2 emission of coal spontaneous combustion and its relation with coal microstructure, China.

Journal of environmental biology·2015

Same author

Insulin Signaling and Glucose Uptake in the Soleus Muscle of 30-Month-Old Rats After Calorie Restriction With or Without Acute Exercise.

The journals of gerontology. Series A, Biological sciences and medical sciences·2015

Same author

Ionic Conductivity Increased by Two Orders of Magnitude in Micrometer-Thick Vertical Yttria-Stabilized ZrO2 Nanocomposite Films.

Nano letters·2015

Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

See all related articles

This summary is machine-generated.

This study introduces a novel two-level co-training framework with bidirectional knowledge exchange, significantly improving image segmentation performance by creating a positive feedback loop between model levels.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Traditional co-training methods often underutilize ensemble learning, leading to inefficient resource allocation.
Existing approaches face limitations in leveraging the full potential of ensemble learning for segmentation tasks.

Purpose of the Study:

To propose an advanced two-level co-training structure that enhances ensemble learning for improved segmentation performance.
To address the performance bottleneck in second-level models caused by the learning capacity of first-level models.

Main Methods:

Implemented a two-level co-training structure with first-level classical co-training models and second-level models using ensemble pseudo-labels.
Introduced a bidirectional knowledge exchange strategy, inspired by pix2pixHD, for feature feedback between model levels.

Keywords:

Medical image segmentation Semi-supervised learning

More Related Videos

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

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

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Jan 12, 2026

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

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

Published on: November 30, 2022

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

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

Published on: April 13, 2013

Integrated these components into a positive feedback loop to enhance overall model performance.

Main Results:

Second-level models demonstrated superior segmentation performance compared to individual first-level models.
The bidirectional knowledge exchange effectively mitigated performance constraints, boosting both first- and second-level model capabilities.
The proposed approach achieved strong competitiveness against state-of-the-art methods on multiple benchmark datasets.

Conclusions:

The novel two-level co-training structure with bidirectional knowledge exchange significantly enhances image segmentation.
This positive feedback loop architecture offers a more effective and resource-efficient approach to ensemble learning in segmentation.
The method shows promising results and competitiveness in the field of semantic segmentation.