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

Effect of mirror use on lower extremity muscle strength of patients with chronic stroke.

Journal of physical therapy science·2018
Same author

[Analysis of population genetic diversity of mosquitoes from Shandong Province based on mitochondrial DNA cytochrome oxidase subunit I gene fragment].

Zhongguo xue xi chong bing fang zhi za zhi = Chinese journal of schistosomiasis control·2018
Same author

Asymmetric Total Synthesis of Lancifodilactone G Acetate. 2. Final Phase and Completion of the Total Synthesis.

The Journal of organic chemistry·2018
Same author

Genotoxicity evaluation of multi-component mixtures of polyaromatic hydrocarbons (PAHs), arsenic, cadmium, and lead using flow cytometry based micronucleus test in HepG2 cells.

Mutation research. Genetic toxicology and environmental mutagenesis·2018
Same author

In Situ Embedded Pseudo Pd-Sn Solid Solution in Micropores Silica with Remarkable Catalytic Performance for CO and Propane Oxidation.

ACS applied materials & interfaces·2018
Same author

Manipulating Refractive Index in Organic Light-Emitting Diodes.

ACS applied materials & interfaces·2018

Related Experiment Video

Updated: Jun 13, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.8K

Medical image analysis using improved SAM-Med2D: segmentation and classification perspectives.

Jiakang Sun1,2, Ke Chen1,2, Zhiyi He1,2

  • 1Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, 610213, Sichuan, China.

BMC Medical Imaging
|September 16, 2024
PubMed
Summary
This summary is machine-generated.

New models SAM-AutoMed and SAM-MedCls enhance medical image analysis. SAM-AutoMed automates segmentation, while SAM-MedCls achieves state-of-the-art classification across modalities.

Keywords:
Attention mechanismClassification and gradingMultimodalSAM-Med2DSegmentation

More Related Videos

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

982
A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

20.3K

Related Experiment Videos

Last Updated: Jun 13, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.8K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

982
A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

20.3K

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Computer Vision

Background:

  • Segment Anything Model (SAM) advanced medical image segmentation (SAM-Med2D).
  • Interactive prompting in SAM-Med2D limits its use in some scenarios.
  • Existing SAM enhancements lack medical image classification applications.

Purpose of the Study:

  • Introduce SAM-AutoMed for automatic medical image segmentation.
  • Develop SAM-MedCls for end-to-end medical image classification.
  • Evaluate performance against existing state-of-the-art models.

Main Methods:

  • Developed SAM-AutoMed by replacing SAM's prompt encoder with MobileNet v3.
  • Constructed SAM-MedCls by integrating SAM-Med2D's encoder with novel attention modules.
  • Validated models on diverse medical imaging datasets.

Main Results:

  • SAM-AutoMed outperformed SAM and SAM-Med2D in segmentation tasks.
  • SAM-MedCls achieved state-of-the-art results in multi-modal medical image classification.
  • Both models demonstrated robust performance across various datasets.

Conclusions:

  • SAM-AutoMed offers an effective solution for automated medical image segmentation.
  • SAM-MedCls shows potential as a universal model for medical image classification.
  • These advancements significantly broaden the utility of large visual models in healthcare.