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

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

Historical roots of hospital-centred operational governance in China: a path dependence analysis and its implications for global health system reform.

BMJ global health·2026

Same author

Environmental Health Literacy Prevalence and Profiles among Shanghai Residents - Shanghai, China, 2020-2024.

China CDC weekly·2026

Same author

Evaluating deep coal rock gas fracturing sweet spot intervals using PSO-ELM algorithm and petrophysical logging data.

Scientific reports·2026

Same author

Association of body mass index and serum markers with immune-related adverse events in lung cancer patients receiving immune checkpoint inhibitors.

Journal of thoracic disease·2026

Same author

An In-Depth Exploration of the Impact of Mixing Ratios in Ball Milling on the Performance of Carbon-Coated LiFe<sub>0.5</sub>Mn<sub>0.5</sub>PO<sub>4</sub> and NCM811 Cathode Material Composites.

Chemphyschem : a European journal of chemical physics and physical chemistry·2026

Same author

Injectable Binary-Amplified Cascade Hydrogels Suppress Post-Incomplete Microwave Ablation Relapse via Integrated Metallo-Metabolic-Immunomodulation.

ACS nano·2026

Search research articles

Related Experiment Video

Updated: Dec 21, 2025

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

Mixed-Supervised Dual-Network for Medical Image Segmentation.

Duo Wang^1,2, Ming Li³, Nir Ben-Shlomo⁴

¹Department of Automation, Tsinghua University, Beijing, China.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

|May 13, 2020

Summary

This summary is machine-generated.

Training deep learning models for medical image segmentation is challenging due to the need for extensive, high-quality data. This study introduces a Mixed-Supervised Dual-Network (MSDN) that effectively uses bounding box annotations to improve segmentation accuracy.

Keywords:

Dual-network Medical image segmentation Mixed-supervised learning Multi-task learning Squeeze-and-Excitation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Dec 21, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Medical Image Analysis
Deep Learning
Computer Vision

Background:

Deep learning models for medical image segmentation demand large, densely annotated datasets, which are costly and time-consuming to create.
Mixed-supervised learning offers a solution by utilizing both dense and weakly labeled data (bounding boxes).
Multi-task learning frameworks can integrate detection and segmentation tasks.

Purpose of the Study:

To propose a novel Mixed-Supervised Dual-Network (MSDN) architecture for medical image segmentation.
To leverage auxiliary detection tasks to enhance segmentation performance.
To investigate the efficacy of information transfer between detection and segmentation networks.

Main Methods:

Developed a dual-network architecture with separate detection and segmentation components.
Implemented connection modules for information transfer between the two networks.
Integrated the 'Squeeze and Excitation' technique within connection modules to optimize information flow.

Main Results:

The MSDN model demonstrated superior performance compared to various baseline methods in experiments.
Effective transfer of information from the detection task significantly aided the segmentation task.
The 'Squeeze and Excitation' modules enhanced the information transfer process.

Conclusions:

The proposed MSDN architecture effectively addresses the data scarcity issue in medical image segmentation.
Mixed-supervised learning combined with dual-network architectures offers a promising direction for medical image analysis.
MSDN provides a robust and efficient solution for training accurate medical image segmentation models with limited dense annotations.