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

Association between amygdala subregions and non-motor symptoms in Parkinson's disease: a fixel-based analysis.

Brain imaging and behavior·2026
Same author

Identification of protein lysine lactylation and potential targets in esophageal squamous cell carcinoma.

Translational cancer research·2026
Same author

PathRWKV: Enhancing Whole Slide Image Inference with Asymmetric Recurrent Modeling.

IEEE transactions on medical imaging·2026
Same author

Integrative pan-cancer analysis of transferrin reveals context-dependent prognostic associations and links to immune and metabolic disease-related programs.

Discover oncology·2026
Same author

Lateral flow immunoassay based on electrospun cellulose acetate nanofibrous membrane for C-reactive protein.

Talanta·2026
Same author

Central lymph node ratio predicting lateral metastasis in pediatric thyroid cancer: a retrospective study.

Frontiers in endocrinology·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
Same journal

Biom3d, a modular framework to host and develop 3D segmentation methods.

Medical image analysis·2026
Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026
Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026
See all related articles

Related Experiment Video

Updated: Apr 16, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K

SSMamba: A self-supervised hybrid state space model for pathological image classification.

Enhui Chai1, Sicheng Chen2, Tianyi Zhang3

  • 1School of Computer Science, Northwest University, Xi'an 710127, China.

Medical Image Analysis
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

SSMamba, a new framework, enhances pathological image analysis by addressing domain shift and improving feature sensitivity. It outperforms existing models on both Region of Interest (ROI) and whole-slide image (WSI) tasks.

Keywords:
Pathological classificationSelf-supervised learningState space model

More Related Videos

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.7K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.8K

Related Experiment Videos

Last Updated: Apr 16, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.7K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.8K

Area of Science:

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

Background:

  • Pathological diagnosis relies heavily on image analysis, with Regions of Interest (ROIs) providing diagnostic evidence.
  • Foundation Models (FMs) using Vision Transformers (ViTs) and self-supervised learning (SSL) are common for ROI analysis but face challenges.
  • Limitations include cross-magnification domain shift, inadequate local-global relationship modeling, and insufficient fine-grained sensitivity.

Purpose of the Study:

  • To introduce SSMamba, a hybrid SSL framework designed for effective fine-grained feature learning in pathological imaging.
  • To address limitations of existing FMs in ROI analysis, including domain shift and sensitivity.
  • To enable robust pathological image analysis without requiring extensive external datasets.

Main Methods:

  • Developed SSMamba, a hybrid SSL framework with three domain-adaptive components: Mamba Masked Image Modeling (MAMIM), Directional Multi-scale (DMS) module, and Local Perception Residual (LPR) module.
  • Implemented a two-stage pipeline: SSL pretraining on target ROI datasets followed by supervised fine-tuning (SFT).
  • Evaluated SSMamba against 11 state-of-the-art (SOTA) pathological FMs on 10 public ROI datasets and 8 SOTA methods on 6 public WSI datasets.

Main Results:

  • SSMamba demonstrated superior performance compared to 11 SOTA pathological FMs across 10 public ROI datasets.
  • The framework also surpassed 8 SOTA methods on 6 public WSI datasets.
  • Results highlight the effectiveness of task-specific architectural designs for pathological image analysis.

Conclusions:

  • SSMamba effectively addresses key limitations in ROI analysis, including domain shift and feature sensitivity.
  • The proposed framework achieves state-of-the-art performance in pathological image analysis tasks.
  • Task-specific architectural designs are crucial for advancing pathological image analysis using foundation models.