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

Extract Nutritional Information from Bilingual Food Labels Using Large Language Models.

Journal of imaging·2025
Same author

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning.

Plants (Basel, Switzerland)·2024
See all related articles

Related Experiment Video

Updated: Sep 3, 2025

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

2.9K

Medical Image Segmentation with Learning Semantic and Global Contextual Representation.

Mohammad D Alahmadi1

  • 1Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 23890, Saudi Arabia.

Diagnostics (Basel, Switzerland)
|July 27, 2022
PubMed
Summary

This study introduces a novel two-pathway model combining Convolutional Neural Networks (CNNs) and Transformers for enhanced medical image segmentation. The model effectively captures both local and global features, improving cancer detection accuracy.

Keywords:
attention mechanismmedical imagesmedical segmentation

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

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

Published on: April 13, 2013

42.8K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.3K

Related Experiment Videos

Last Updated: Sep 3, 2025

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

2.9K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

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

Published on: April 13, 2013

42.8K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate medical image segmentation is crucial for disease diagnosis and treatment planning.
  • U-Net models are standard but struggle with long-range dependencies due to CNN locality.
  • Transformer models excel at global context but lack local detail.

Purpose of the Study:

  • To develop an improved medical image segmentation model.
  • To address the limitations of U-Net and Transformer architectures.
  • To enhance cancer detection and analysis through better segmentation.

Main Methods:

  • Proposed a dual-encoder architecture with parallel CNN and Transformer paths.
  • CNN path captures local semantic representations.
  • Transformer path extracts long-range contextual dependencies.
  • Features from both paths are adaptively fused for a unified representation.

Main Results:

  • The proposed model effectively integrates local and global feature extraction.
  • Demonstrated the capability to generate rich and generic representation features.
  • Achieved high efficiency in fine-grained semantic segmentation tasks.

Conclusions:

  • The novel two-parallel-encoder model offers a significant advancement in medical image segmentation.
  • This approach enhances the ability to model both local and global image features.
  • The method shows promise for improving diagnostic accuracy in medical imaging applications.