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

A Pediatric Knee Exoskeleton With Real-Time Adaptive Control for Overground Walking in Ambulatory Individuals With Cerebral Palsy.

Frontiers in robotics and AI·2021
Same author

Neurobiological substrates of the positive formal thought disorder in schizophrenia revealed by seed connectome-based predictive modeling.

NeuroImage. Clinical·2021
Same author

The effect of pantoprazole and somatostatin combined with thrombin in the treatment of non-esophagogastric varicosity upper gastrointestinal bleeding.

American journal of translational research·2021
Same author

PDL1-positive exosomes suppress antitumor immunity by inducing tumor-specific CD8<sup>+</sup> T cell exhaustion during metastasis.

Cancer science·2021
Same author

Reshaping cell line development and CMC strategy for fast responses to pandemic outbreak.

Biotechnology progress·2021
Same author

Apoptotic vesicles restore liver macrophage homeostasis to counteract type 2 diabetes.

Journal of extracellular vesicles·2021

Related Experiment Video

Updated: Jul 6, 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

2.8K

MD-UNet: a medical image segmentation network based on mixed depthwise convolution.

Yun Liu1, Shuanglong Yao1, Xing Wang2

  • 1School of Information Science and Engineering, Linyi University, Linyi, 276000, China.

Medical & Biological Engineering & Computing
|December 29, 2023
PubMed
Summary

This study introduces MD-UNet, a novel U-shaped network for medical image segmentation. It improves lesion area extraction by addressing intra-class variability and enhancing feature redundancy, leading to better cancer diagnosis.

Keywords:
Depthwise convolutionMDABMedical image segmentationUNet

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

405
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

2.5K

Related Experiment Videos

Last Updated: Jul 6, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
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

2.5K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Accurate lesion segmentation is crucial for cancer diagnosis and treatment planning.
  • Current UNet-based medical image segmentation methods struggle with intra-class variability and feature redundancy.

Purpose of the Study:

  • To propose MD-UNet, a U-shaped network designed to improve medical image segmentation.
  • To address limitations in existing methods by enhancing feature extraction and handling image variability.

Main Methods:

  • Introduced a Mixed depthwise convolution residual module (MDRM) and a Mixed depthwise convolution attention block (MDAB).
  • MDAB captures local and global dependencies, mitigates intra-class differences, and generates multiple feature mappings.
  • Developed the MD-UNet architecture integrating MDRM for enhanced segmentation.

Main Results:

  • MD-UNet demonstrated improved segmentation accuracy on the ISIC2018 dataset compared to UNeXt.
  • Achieved a 1.33% increase in Dice coefficient and a 1.91% increase in Intersection over Union (IoU).

Conclusions:

  • MD-UNet effectively addresses intra-class variability and feature redundancy in medical image segmentation.
  • The proposed method shows significant potential for improving clinical diagnosis through more accurate lesion area extraction.