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: Jul 16, 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

LightVM-SparseUNet: A lightweight medical image segmentation framework via Vision Mamba and sparse attention.

Haojie Fan1, Kang Xu2, Xiaoyu Hou3

  • 1Liaoning Petrochemical University, No.1, Dandong Road West, Wanghua District, Fushun, Liaoning, 113001, China.

Biomedical Physics & Engineering Express
|July 14, 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 proliferation-inducing ligand enhances the anti-tumor effect of BCMA CAR T-cell through inhibition of soluble BCMA.

Biochimica et biophysica acta. Molecular basis of disease·2026
Same author

Regulatory B-cell states in NSCLC immunotherapy resistance: mechanisms, spatial context and translational implications.

Cancer immunology, immunotherapy : CII·2026
Same author

Dissociable peripheral and central mechanisms of monoacylglycerol lipase inhibition on pain- and depression-related behaviors in a rat model of neuropathic pain.

Pain·2026
Same author

A novel fully visualized transparent channel in posterior uniportal endoscopic spine surgery: a paradigm shift for nerve root exposure and decompression under direct visualization.

Journal of neurosurgery. Spine·2026
Same author

Decoding α-MoC<sub>1-</sub> <sub>x</sub> Nanoparticle Formation in Continuous Flow via Machine Learning.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Anti-BCMA/GPRC5D CAR T in relapsed or refractory multiple myeloma patients with extraosseous extramedullary disease.

Blood·2026

This study introduces LightVM-SparseUNet, an ultra-lightweight medical image segmentation framework using State Space Models (SSMs). It achieves competitive segmentation performance with significantly reduced parameters and computational cost for edge devices.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Traditional Convolutional Neural Networks (CNNs) and Transformer architectures face challenges with parameter redundancy and computational complexity.
  • These limitations hinder the deployment of medical image segmentation models on resource-constrained edge devices.

Purpose of the Study:

  • To propose LightVM-SparseUNet, an ultra-lightweight medical image segmentation framework.
  • To address the deployment challenges of medical imaging AI on edge devices.

Main Methods:

  • Developed a Multi-path Visual Mamba (MVM) module for efficient feature extraction with linear complexity.
  • Integrated a Sparse-Sampling Self-Attention (SSSA) mechanism into U-shaped skip connections to capture long-range spatial dependencies efficiently.
Keywords:
LightweightMedical image segmentationMulti-path Visual MambaSparse-sampling self-attention

Related Experiment Videos

Last Updated: Jul 16, 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

Main Results:

  • LightVM-SparseUNet achieves segmentation performance competitive with state-of-the-art large-scale models.
  • The model demonstrates extreme lightweight design with only 0.08 million parameters and 0.16 GFLOPs computational overhead.
  • Experimental validation on two public datasets confirms the model's efficacy.

Conclusions:

  • LightVM-SparseUNet offers a highly practical and efficient solution for medical image segmentation on edge devices.
  • The proposed framework significantly reduces computational complexity and parameter count while maintaining high performance.