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: Jun 4, 2026

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
06:34

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

Published on: August 8, 2025

Adapting SAM to nuclei instance segmentation and classification via Cooperative Fine-Grained Refinement.

Jingze Su1, Tianle Zhu1, Jiaxin Cai1

  • 1College of Computer and Data Science, Fuzhou University, Fuzhou, China.

Medical Image Analysis
|June 2, 2026
PubMed
Summary

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

Deep Learning for Quality Control and Multimodal Integration of Shear Wave Elastography in Breast Lesion Characterization.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2026
Same author

Deep Learning for Point-of-Care Ultrasound M-Mode Analysis.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2026
Same author

Deep Learning for Automated Infant Hip Ultrasound: Toward Robust Generalization across Disease Spectrum and Devices.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2026
Same author

MedLP-HAFB-CLIP: Hierarchical Adaptive Large Model With Learnable Medical Prompts for Level II Ultrasound Standard Plane Identification.

Ultrasound in medicine & biology·2026
Same author

Deep Learning for Automated Quantification and Differential Diagnosis of Cutaneous Mastocytoma on Dynamic Ultrasound.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2026
Same author

Deep Learning for Ultrasound-Guided Prostate Biopsy: Toward Automated Targeting and Complication Prediction.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2026
Same journal

HiVLR: Hierarchical Vision-Language Reasoning for interpretable zero-shot radiography image understanding.

Medical image analysis·2026
Same journal

FAA-Net: Fetal abdominal anomaly diagnosis in prenatal ultrasound via LLM-enhanced multi-instance learning.

Medical image analysis·2026
Same journal

Wavelet-inspired diffusion model with near-field constraint for real-time echocardiography dehazing.

Medical image analysis·2026
Same journal

Co-assistant networks by pathology foundation model and convolutional neural network for gigapixel whole slide image analysis.

Medical image analysis·2026
Same journal

MBAS2024: A large-scale benchmark for multi-class bi-atrial segmentation in multi-center contrast-enhanced MRIs.

Medical image analysis·2026
Same journal

Respiratory motion augmentation for personalized super-resolution (RMApSR) of 3D cine MR images in MRI-guided radiotherapy.

Medical image analysis·2026
See all related articles
This summary is machine-generated.

This study introduces a new method for nuclei instance segmentation in computational pathology, improving cancer diagnosis. The approach efficiently adapts the Segment Anything Model (SAM) for medical images, achieving state-of-the-art results with fewer parameters.

Area of Science:

  • Computational pathology
  • Medical image analysis
  • Artificial intelligence in healthcare

Background:

  • Nuclei instance segmentation is vital for cancer diagnosis and prognosis.
  • The Segment Anything Model (SAM) shows promise but struggles with medical imaging's local structural features.
  • Full SAM fine-tuning is computationally expensive for specialized tasks.

Purpose of the Study:

  • To develop a parameter-efficient framework for adapting SAM to nuclei instance segmentation.
  • To enhance SAM's perception of local structural features crucial for medical imaging.
  • To achieve accurate nuclei segmentation with reduced computational cost.

Main Methods:

  • Proposing Cooperative Fine-Grained Refinement of SAM (CFGR-SAM).
  • Utilizing a Multi-scale Adaptive Local-aware Adapter to augment the SAM backbone with minimal parameters and local feature perception.
Keywords:
Computational pathologyNuclei instance segmentationParameter-efficient fine-tuningSegment anything model

More Related Videos

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images
14:28

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images

Published on: July 15, 2020

Related Experiment Videos

Last Updated: Jun 4, 2026

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
06:34

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

Published on: August 8, 2025

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images
14:28

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images

Published on: July 15, 2020

  • Employing a Hierarchical Modulated Fusion Module to aggregate multi-level features for spatial detail preservation.
  • Implementing Boundary-Guided Mask Refinement for sharper segmentation using explicit boundary supervision.

    • Main Results:

    • CFGR-SAM significantly enhances local perception and preserves fine-grained spatial details.
    • The method achieves state-of-the-art performance on three challenging nuclei instance segmentation benchmarks.
    • The framework requires substantially fewer trainable parameters compared to existing methods.

    Conclusions:

    • CFGR-SAM effectively transfers SAM's knowledge to nuclei instance segmentation.
    • The proposed cooperative components enable accurate segmentation by improving local perception, detail preservation, and boundary refinement.
    • This parameter-efficient approach offers a viable solution for computational pathology applications.