Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Preclinical evaluation of [<sup>68</sup>Ga]Ga-MRCP: a potential radiotracer for imaging PD-L1 expression in colorectal cancer.

Bioorganic chemistry·2026

Same author

When One Sequence Is Enough-And When It Isn't.

Radiology. Artificial intelligence·2026

Same author

Transplant-ready? Evaluating AI lung segmentation models in candidates with severe lung disease.

Journal of medical imaging (Bellingham, Wash.)·2026

Same author

Beyond technical access in digital eldercare: how ethical lag shapes stratified responsiveness to institutional welfare in rural China.

BMC geriatrics·2026

Same author

Modulation of lysozyme amyloid fibrillation by three structurally similar dihydroxy-coumarins: A comparative analysis.

Bioorganic chemistry·2026

Same author

Deep learning automates Cobb angle measurement compared with multi-expert observers.

BJR artificial intelligence·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 19, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Segment anything model for medical image analysis: An experimental study.

Maciej A Mazurowski¹, Haoyu Dong², Hanxue Gu²

¹Department of Radiology, Duke University, Durham, NC, 27708, USA; Department of Electrical and Computer Engineering, Duke University, Durham, NC, 27708, USA; Department of Computer Science, Duke University, Durham, NC, 27708, USA; Department of Biostatistics & Bioinformatics, Duke University, Durham, NC, 27708, USA.

Medical Image Analysis

|August 18, 2023

Summary

This summary is machine-generated.

The Segment Anything Model (SAM) shows varied performance in medical image segmentation, excelling with box prompts on some datasets but struggling with others. Iterative prompting offers limited gains for SAM compared to other methods.

Keywords:

Deep learning Foundation models Segmentation

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 19, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Computer Vision
Artificial Intelligence

Background:

Medical image segmentation is crucial but hindered by limited annotated data.
Foundation models like Segment Anything Model (SAM) offer potential solutions.
SAM, trained on natural images, needs evaluation for specialized medical domains.

Purpose of the Study:

To extensively evaluate SAM's zero-shot medical image segmentation capabilities.
To compare SAM's performance against other interactive segmentation methods.
To identify factors influencing SAM's segmentation accuracy across diverse medical datasets.

Main Methods:

Evaluated SAM on 19 diverse medical imaging datasets (various modalities and anatomies).
Simulated interactive segmentation using point and box prompts.
Compared SAM's performance (IoU) with RITM, SimpleClick, and FocalClick.

Main Results:

SAM's performance varied significantly across datasets (IoU 0.1135 for spine MRI to 0.8650 for hip X-ray).
Box prompts outperformed point prompts; performance was better for well-circumscribed objects.
SAM surpassed other methods with single-point prompts but iterative prompting yielded limited improvement.

Conclusions:

SAM demonstrates impressive zero-shot segmentation for specific medical imaging tasks.
Performance is moderate to poor for other medical datasets, requiring careful application.
SAM has potential for automated medical image segmentation, but domain-specific validation is essential.