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

Post-marketing safety of tarlatamab in small cell lung cancer based on FAERS and WHO-VigiAccess with SHAP-based interpretable machine learning analysis of immune-related adverse events.

Frontiers in pharmacology·2026
Same author

Effects and Mechanisms of Wrist-Ankle Acupuncture on Inflammatory Pain in the Rat Gastrocnemius Muscle.

Journal of pain research·2026
Same author

A retrospective cohort study comparing the effects on inflammatory response and clinical outcomes of vancomycin-PMMA versus vancomycin-sulfate calcium in chronic osteomyelitis.

Annals of medicine·2026
Same author

Pathological Mechanism-Inspired Biomimetic Nano-Senotherapy for Reversing Experimental Atherosclerosis in ApoE<sup>-/-</sup> Mice.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Hierarchically Chiral Silver Nanoclusters Mediated Enantioselective Glutathione Depletion and Intracellular Self-Assembly for Enhanced Anticancer Therapy.

Angewandte Chemie (International ed. in English)·2026
Same author

Spatial and temporal variation in bacterial-archaeal community and niche differentiation of denitrifying anaerobic methane-oxidizing microbes in grass carp (<i>Ctenopharyngodon idellus</i>) aquaculture ponds of Northern China.

Frontiers in microbiology·2026

Related Experiment Video

Updated: Apr 23, 2026

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

3.6K

Text-Guided Multi-stage Cross-perception Network for Medical Image Segmentation.

Gaoyu Chen1, Haixia Pan2, Yuhan Tian3

  • 1College of Software, Beihang University, Beijing, China.

Journal of Imaging Informatics in Medicine
|April 21, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a new text-guided network (TMC) for medical image segmentation, improving lesion localization accuracy. The TMC method enhances cross-modal understanding, outperforming traditional and existing text-guided approaches in clinical applications.

Keywords:
Attention mechanismCross-perceptionMedical image segmentationVision-language

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

989
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

3.8K

Related Experiment Videos

Last Updated: Apr 23, 2026

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

3.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

989
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

3.8K

Area of Science:

  • Medical imaging
  • Artificial intelligence
  • Computer-aided diagnosis

Background:

  • Medical image segmentation is vital for diagnosis, treatment planning, and monitoring.
  • Traditional methods like U-Net struggle with semantic expression and interactivity.
  • Existing text-guided methods face challenges in cross-modal interaction and feature representation.

Purpose of the Study:

  • To develop an advanced text-guided network for precise medical image segmentation.
  • To overcome limitations in semantic understanding and cross-modal feature representation.
  • To enhance the accuracy and consistency of lesion localization using text prompts.

Main Methods:

  • Proposing the text-guided multi-stage cross-perception network (TMC).
  • Implementing a multi-stage cross-attention module (MCM) for fine-grained semantic understanding.
  • Utilizing a multi-stage alignment loss (MA Loss) for improved cross-modal semantic consistency.

Main Results:

  • TMC achieved high Dice scores: 84.65% (QaTa-COV19), 78.39% (MosMedData), and 88.09% (Duke-Breast-Cancer-MRI).
  • Demonstrated superior performance compared to U-Net-based networks.
  • Outperformed existing text-guided segmentation methods across multiple datasets.

Conclusions:

  • The proposed TMC network significantly improves medical image segmentation accuracy.
  • TMC effectively enhances cross-modal interaction and feature representation for better lesion identification.
  • This approach offers a promising advancement for clinical auxiliary diagnosis and disease monitoring.