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: Jan 7, 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

3.3K

StarMA Net: A star-shape multi-scale attention network for medical imaging classification.

Junyang Cao1,2, Junrui Lv3, Xuegang Luo3

  • 1School of Computer Science, China West Normal University, Nanchong 637000, Sichuan, China.

Iscience
|January 5, 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

A parallel UNet integrating KAN and mamba for medical image segmentation.

Scientific reports·2026
Same author

Hyperspectral remote sensing image classification based on domain-level complementarity of spatial-spectral component.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

LIIA -Net: A lightweight illumination iterative adjustment network for low-light image enhancement.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Pre- to post-contrast medical image synthesis with outline-guide accelerate diffusion model.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Dual-modality visual feature flow for medical report generation.

Medical image analysis·2024
Same author

CGFTrans: Cross-Modal Global Feature Fusion Transformer for Medical Report Generation.

IEEE journal of biomedical and health informatics·2024

We introduce StarMA, a novel attention mechanism for medical image classification. StarMA enhances feature representation by effectively utilizing spatial information and modeling inter-channel interactions, improving diagnostic accuracy.

Area of Science:

  • Computer Vision
  • Medical Imaging
  • Machine Learning

Background:

  • Medical image classification is vital for clinical diagnosis but faces challenges like limited characterization, category differentiation issues, and individual variations.
  • Existing attention mechanisms improve feature representation but often fail to effectively use spatial information and model inter-channel interactions.

Purpose of the Study:

  • To propose a novel attention mechanism, StarMA, to address the limitations of existing methods in medical image classification.
  • To enhance the utilization of spatial information and inter-channel interactions for improved diagnostic accuracy.

Main Methods:

  • StarMA employs axial decomposition to retain spatial information across orientations within channels, improving complex structure perception.
  • A star-shaped projection into high-dimensional nonlinear space strengthens inter-channel interactions and inter-class discriminability.
Keywords:
BioinformaticsComputer modelingMedical imaging

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721

Related Experiment Videos

Last Updated: Jan 7, 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

3.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721
  • A cross-spatial aggregation learning strategy integrates multi-scale contextual information to handle intra-class variability.

    • Main Results:

    • StarMA Net, built upon StarMA, was evaluated on five diverse medical image datasets.
    • Comparative experiments showed StarMA Net outperforms advanced algorithms in effectiveness and robustness.

    Conclusions:

    • StarMA significantly enhances medical image classification by improving spatial information utilization and inter-channel modeling.
    • StarMA Net offers a robust and effective solution for clinical diagnosis, addressing key challenges in medical datasets.