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: Mar 21, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

854

Dual-branch attention network with deep split convolution and multi-dimensional transformers for medical image

Debao Li1, Cheng Yuan2, Yexiang Yao3

  • 1School of Public Health, Qiqihar Medical University, Qiqihar, 161003, China. lidebao2000@163.com.

Scientific Reports
|March 20, 2026
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

Tertiary lymphoid structures in gastrointestinal cancer: orchestrating tumour microenvironmental immune subcycles to elegantly amplify the cancer immunity cycle.

Annals of medicine·2026
Same author

Electrochemical in-biosensing computing.

National science review·2026
Same author

Valence-State-Dependent Surface Lattice Oxygen in CeO<sub>2</sub>‑Modified VPO Catalysts: Elucidating the Mechanism of <i>n</i>‑Butane Selective Oxidation to Maleic Anhydride.

JACS Au·2026
Same author

A bioinspired photoelectrochemical synapse for neurotransmitter-mediated in-sensor computing.

Biosensors & bioelectronics·2026
Same author

Toothpastes containing potassium nitrate alone versus potassium nitrate combined with aluminum lactate in reducing dentin hypersensitivity: a randomized controlled trial.

BDJ open·2026
Same author

Therapeutic Targets for Pediatric Pulmonary Vein Stenosis: Insights from Animal Models.

Children (Basel, Switzerland)·2026

This study introduces the dual-branch attention network (D3T-Net) for precise medical image segmentation. D3T-Net improves the accuracy of segmenting liver and lesions, aiding in disease assessment and precision medicine.

Area of Science:

  • Medical Image Analysis
  • Artificial Intelligence in Medicine
  • Computational Pathology

Background:

  • Accurate segmentation of anatomical structures and pathologies is crucial for disease assessment.
  • Current segmentation algorithms struggle with morphological heterogeneity, leading to inaccurate results.
  • Obscured contours and compromised accuracy hinder reliable medical image analysis.

Purpose of the Study:

  • To develop an advanced deep learning model for precise medical image segmentation.
  • To address the limitations of existing algorithms in handling complex anatomical variations.
  • To improve the segmentation accuracy of liver and associated lesions for enhanced diagnostic capabilities.

Main Methods:

  • Proposed a dual-branch attention network (D3T-Net) combining deep split convolution and multi-dimensional Transformer.

More Related Videos

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

3.7K

Related Experiment Videos

Last Updated: Mar 21, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

854
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

3.7K
  • Implemented parallel CNN and Transformer branches for local and global feature extraction.
  • Introduced direction-aware interaction attention and cross-attention mechanisms for robust feature exchange and integration.
  • Utilized multi-scale fusion skip connections to enhance feature transfer and boundary retention.

    • Main Results:

    • D3T-Net demonstrated superior performance compared to existing benchmarks in segmenting liver and lesions.
    • The network effectively captured local details and global contextual information.
    • Improved segmentation accuracy, particularly for small objects and complex boundaries.

    Conclusions:

    • D3T-Net offers significant advancements in automated medical image segmentation.
    • The proposed method enhances diagnostic accuracy, supporting precision medicine in hepatology.
    • This approach provides robust support for clinical decision-making in liver disease management.