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

Amphiphilic Lipid-Single-Stranded DNA Conjugate-Mediated Cell Surface Engineering for Programmable Intercellular Tethering and Immune Synapse Formation.

Biomaterials research·2026

Same author

Surface Engineering of NK Cells with Poly-L-Glutamic Acid Enhances Tumor-Selective Immunotherapy Against Ovarian Cancer.

Cells·2026

Same author

A 27-year-old woman presenting with fever and neck mass sensation.

Journal of Yeungnam medical science·2026

Same author

Circulating 1-Methylnicotinamide Predicts Dupilumab Response in Adult Asthma: A Prediction Model.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2026

Same author

Size exchange and vault response in posterior chamber phakic intraocular lens implantation: 12 years at a high-volume center.

Journal of cataract and refractive surgery·2026

Same author

A harmonized global prediction of biodegradable dissolved organic carbon in freshwater systems using optical indices and machine learning.

Environmental research·2026

Search research articles

Related Experiment Video

Updated: Oct 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation.

Chae Eun Lee¹, Minyoung Chung², Yeong-Gil Shin¹

¹Department of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea.

Computer Methods and Programs in Biomedicine

|November 28, 2021

Summary

This summary is machine-generated.

This study introduces a novel Siamese representation learning method for abdominal multi-organ segmentation. The approach improves medical image segmentation accuracy with limited data by enhancing feature representation space.

Keywords:

Abdominal ct segmentation Medical image segmentation Multi-organ segmentation Representation learning Siamese network

More Related Videos

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

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

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

Published on: August 23, 2017

Related Experiment Videos

Last Updated: Oct 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

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

Published on: August 23, 2017

Area of Science:

Medical Image Analysis
Deep Learning
Computer Vision

Background:

Limited annotations in medical imaging hinder deep learning segmentation.
Existing methods often overlook cross-volume context and focus on decision space relations.

Purpose of the Study:

To propose a novel voxel-level Siamese representation learning method for abdominal multi-organ segmentation.
To improve the representation space for enhanced segmentation accuracy with limited datasets.

Main Methods:

Enforces voxel-wise feature relations in the representation space using contrastive learning principles.
Suppresses same-class voxel relations without negative samples.
Introduces multi-resolution context aggregation for global and local feature encoding.

Main Results:

Achieved a 2% higher Dice score coefficient on a multi-organ dataset compared to existing methods.
Demonstrated improvements attributed to a disentangled feature space via qualitative visualizations.

Conclusions:

The proposed representation learning method effectively encodes high-level features from limited medical imaging data.
Achieved superior accuracy in medical image segmentation over contrastive loss-based methods.
The method is versatile and can be integrated into other networks without extra inference parameters.