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
  1. Home
  3. Research Domains
  1. Home
  3. Research Domains

Related Concept Videos

  • Information And Computing Sciences
  • Artificial Intelligence
  • Natural Language Processing
  • Automated Lumbar Spine Segmentation In Mri Using An Enhanced U-net With Inception Module And Dual-output Mechanism.
  • Information And Computing Sciences
  • Artificial Intelligence
  • Natural Language Processing
  • Automated Lumbar Spine Segmentation In Mri Using An Enhanced U-net With Inception Module And Dual-output Mechanism.

    • Related Experiment Video

    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

    Automated lumbar spine segmentation in MRI using an enhanced U-Net with inception module and dual-output mechanism.

    Jaysel Theresa Silveira1, Girisha S1, Poornima Panduranga Kundapur2

    • 1Department of Data Science and Computer Applications, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.

    Scientific Reports
    |November 10, 2025

    View abstract on PubMed

    Summary
    This summary is machine-generated.

    This study introduces an enhanced U-Net model for precise lumbar spine MRI segmentation. The deep learning approach improves the identification of vertebrae, intervertebral discs (IVDs), and the spinal canal for better diagnosis.

    Keywords:
    Binary segmentationDual-output mechanismInception moduleLumbar spine segmentationMulticlass segmentationSemantic segmentationU-Net

    More Related Videos

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    9.4K

    Related Experiment Videos

    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
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    9.4K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Radiology

    Background:

    • Accurate segmentation of lumbar spine structures is vital for diagnosing spinal disorders.
    • Deep learning semantic segmentation has advanced medical image analysis.

    Purpose of the Study:

    • To propose an enhanced U-Net model for improved lumbar spine MRI segmentation.
    • To achieve superior accuracy in segmenting vertebrae, intervertebral discs (IVDs), and the spinal canal.

    Main Methods:

    • Developed an enhanced U-Net with an Inception module for multi-scale features and a dual-output mechanism.
    • Trained and evaluated the model on the SPIDER lumbar spine MRI dataset.
    • Compared performance against U-Net, ResUNet, Attention U-Net, and TransUNet, assessing various metrics including mIoU.

    Main Results:

    • The proposed model achieved superior segmentation accuracy, outperforming baseline models.
    • Achieved a mean Intersection over Union (mIoU) of 0.8974 and an accuracy of 0.9742.
    • Demonstrated improved boundary delineation and effective handling of class imbalance, with Dice loss proving most effective.

    Conclusions:

    • The enhanced U-Net provides a precise and efficient solution for automated lumbar spine segmentation in MRI.
    • The Inception module and dual-output mechanism enhance feature extraction and model stability.
    • This approach supports improved diagnostic workflows in medical imaging.