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

GatorSC: multi-scale cell and gene graphs with mixture-of-experts fusion for single-cell transcriptomics.

Briefings in bioinformatics·2026
Same author

Population-scale characterization of the oral microbiome and associations with metabolic health.

Nature communications·2026
Same author

The effect of multi-strain probiotics on frailty in osteoarthritis patients: a randomized trial focusing on intestinal leak repair.

European journal of clinical nutrition·2026
Same author

Improvement in postural imbalance with intake of resveratrol (polyphenolic phytoalexin) in patients of knee osteoarthritis.

Explore (New York, N.Y.)·2026
Same author

GatorSC: Multi-Scale Cell and Gene Graphs with Mixture-of-Experts Fusion for Single-Cell Transcriptomics.

bioRxiv : the preprint server for biology·2025
Same author

A hybrid attention network for accurate breast tumor segmentation in ultrasound images.

Scientific reports·2025

Related Experiment Video

Updated: Jul 11, 2025

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

2.8K

LDMRes-Net: A Lightweight Neural Network for Efficient Medical Image Segmentation on IoT and Edge Devices.

Shahzaib Iqbal, Tariq M Khan, Syed S Naqvi

    IEEE Journal of Biomedical and Health Informatics
    |November 8, 2023
    PubMed
    Summary

    We developed LDMRes-Net, a lightweight neural network for fast medical image segmentation on edge devices. This efficient model achieves high accuracy in retinal image analysis, improving real-time clinical applications.

    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

    435
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K

    Related Experiment Videos

    Last Updated: Jul 11, 2025

    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

    2.8K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    435
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K

    Area of Science:

    • Artificial Intelligence
    • Medical Imaging
    • Computer Vision

    Background:

    • Conventional U-Net models struggle with real-time medical image segmentation demands on IoT and edge platforms.
    • Challenges include speed, efficiency, and resource constraints in clinical applications like disease monitoring and image-guided surgery.

    Purpose of the Study:

    • Introduce LDMRes-Net, a lightweight dual-multiscale residual block-based convolutional neural network.
    • Address limitations of existing models for efficient medical image segmentation on resource-constrained devices.

    Main Methods:

    • Developed a novel dual multiscale residual block architecture for refined feature extraction at multiple scales.
    • Optimized filter selection to minimize overlap, reduce training time, and enhance computational efficiency.
    • Evaluated LDMRes-Net on retinal image segmentation for vessels and hard exudates.

    Main Results:

    • LDMRes-Net demonstrates a remarkably low parameter count (0.072 M), ideal for edge computing.
    • Achieved high segmentation accuracy, robustness, and generalizability in ophthalmology applications.
    • Showcased significant improvements in speed and computational efficiency compared to conventional models.

    Conclusions:

    • LDMRes-Net offers an efficient solution for accurate and rapid medical image segmentation on IoT and edge platforms.
    • The model's performance holds promise for real-time medical image analysis in resource-limited settings.
    • Facilitates improved healthcare outcomes through advanced, accessible diagnostic tools.