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 29, 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

Vision mamba augmented segment anything model for medical image segmentation.

Zimao Li1,2, Hongyan Zhao1,2, Fan Yin1,3

  • 1College of Computer Science, South-Central Minzu University, Wuhan, China.

Medical Physics
|May 28, 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

Machine learning to identify novel bleeding and residual thromboembolic risks in patients on anticoagulation.

Journal of thrombosis and thrombolysis·2026
Same author

Highly Dispersed Co/CoO Nanoparticles Anchored on N-Doped Biochar Enhanced Peroxymonosulfate Activation for Efficient Norfloxacin Degradation.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Lead-Site Myocardial Scar Predicts Echocardiographic Response to Left Bundle Branch Area Pacing.

Pacing and clinical electrophysiology : PACE·2026
Same author

Recent advances in the analysis of unsaturated fatty acids in biological samples based on chemical derivatization and mass spectrometry techniques.

Journal of pharmaceutical analysis·2026
Same author

Captodative Radicals Coupling Into Homochiral Molecular Nanotubes With Conglomerate Crystallization.

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

Spatial distribution analysis of tertiary lymphoid structures in esophageal squamous cell carcinoma predicts patient survival and response to neoadjuvant chemo-immunotherapy.

Journal of translational medicine·2026

VM-MedSAM enhances medical image segmentation by improving efficiency and accuracy. This novel model significantly reduces computational costs and model size while boosting segmentation performance for various medical conditions.

Area of Science:

  • Medical imaging and artificial intelligence
  • Computer vision for healthcare applications
  • Deep learning for medical image analysis

Background:

  • Medical image segmentation is vital for diagnosis and treatment but faces challenges with current models like SAM and MedSAM.
  • Existing methods struggle with high computational demands and insufficient accuracy for detailed medical image features.

Purpose of the Study:

  • To develop a more efficient and precise medical image segmentation model, addressing the limitations of existing approaches.
  • Introduce VM-MedSAM, a novel model designed for improved performance and reduced resource consumption.

Main Methods:

  • VM-MedSAM is inspired by the Mamba architecture, utilizing a vision backbone (RVM+) and an optimized image encoder from MedSAM.
  • The model freezes the prompt encoder and optimizes the image encoder, reducing parameters and enhancing training efficiency.
Keywords:
computational resource consumptionmedical image segmentationmedsam

More Related Videos

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

Related Experiment Videos

Last Updated: May 29, 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

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

  • Validation was performed on a diverse medical image dataset of 12 abdominal organs.

    • Main Results:

    • VM-MedSAM demonstrated improved segmentation accuracy for lung cancer and brain tumors, with slight gains in abdominal organ segmentation compared to MedSAM.
    • Significant reductions in computational resources were observed: 65.11% fewer parameters, 3.82x faster training, and an 85.41% smaller model size.
    • The model proves effective in handling detailed features crucial for accurate medical image segmentation.

    Conclusions:

    • VM-MedSAM offers an effective solution to the high computational cost and accuracy limitations in current medical image segmentation.
    • The model's enhanced performance and efficiency present it as a promising advancement for medical image analysis and clinical applications.