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: May 22, 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

CDM-UNet: Content-Driven Enhanced Mamba Model for Medical Image Segmentation.

Fan Zhang1,2, Hui Chen2, Binjie Wang3

  • 1Medical Imaging Research Institute, Huaihe Hospital of Henan University, Kaifeng, 475004, China.

Interdisciplinary Sciences, Computational Life Sciences
|May 21, 2026
PubMed
Summary
This summary is machine-generated.

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 Bimodal Graph Neural Network with Transfer Learning and Contrastive Learning for Protein-Protein Interaction Site Prediction.

Interdisciplinary sciences, computational life sciences·2026
Same author

Prediction of Epilepsy Seizure Based on Cepstrum Analysis and Deep Learning.

Interdisciplinary sciences, computational life sciences·2025
Same author

NPI-HetGNN: A Prediction Model of ncRNA-Protein Interactions Based on Heterogeneous Graph Neural Networks.

Interdisciplinary sciences, computational life sciences·2025
Same author

ECMHA-PP: A Breast Cancer Prognosis Prediction Model Based on Energy-Constrained Multi-Head Self-Attention.

Proteomics. Clinical applications·2024
Same author

MFCC-CNN: A patient-independent seizure prediction model.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2024
Same author

Rotating Stomata Measurement Based on Anchor-Free Object Detection and Stomata Conductance Calculation.

Plant phenomics (Washington, D.C.)·2023

This study introduces CDM-UNet, a novel deep learning model for medical image segmentation. CDM-UNet enhances feature representation and fusion, outperforming existing methods in accuracy and efficiency.

Area of Science:

  • Medical Image Analysis
  • Deep Learning
  • Computer Vision

Background:

  • Medical image segmentation is crucial for diagnosis and treatment planning.
  • Deep learning models like CNNs and ViTs have advanced segmentation but face limitations with complex structures and computational demands.
  • Existing methods struggle with intricate anatomy, unclear boundaries, and scale variations in medical images.

Purpose of the Study:

  • To introduce CDM-UNet, a novel deep learning model for improved medical image segmentation.
  • To enhance feature representation and fusion by combining Mamba's global modeling with lightweight attention.
  • To address limitations of current models in handling complex anatomical structures and computational resources.

Main Methods:

  • Developed CDM-UNet, integrating Mamba's global feature modeling with lightweight attention mechanisms.
Keywords:
Content-driven attentionMedical image segmentationVision mamba

Related Experiment Videos

Last Updated: May 22, 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

  • Introduced the Content Driven Mamba Block (CDMB) as a core component.
  • Incorporated a SCConv-Based Attention Gate (SAG) module to filter irrelevant information.

    • Main Results:

    • CDM-UNet demonstrated superior performance on ISIC17, ISIC18, and Synapse datasets.
    • Achieved higher Dice Similarity Coefficient (DSC) and mean Intersection over Union (mIoU) compared to mainstream models.
    • Showcased excellent segmentation accuracy for intricate medical images.

    Conclusions:

    • CDM-UNet offers improved feature representation and fusion for medical image segmentation.
    • The hybrid Mamba model shows significant potential for advancing medical image analysis.
    • CDM-UNet provides a more effective and efficient solution for complex medical image segmentation tasks.