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: Jun 27, 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

CT-Based Liver Segmentation for Liver Surgery: A Hybrid Approach Based on 3D U-Net-ELM Model.

Zeki Ogut1, Eser Sert2, Ertugrul Kaya3

  • 1Department of Surgery, Elazig Fethi Sekin City Hospital, Elazig 23300, Türkiye.

Biomedicines
|June 26, 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

ABR-UNet3D: Aspect-Aware Boundary-Resilient Attention for Robust Cardiac MRI Segmentation.

Diagnostics (Basel, Switzerland)·2026
Same author

An Attention-Enhanced RegNetY Framework for Detection and Classification of Vertical Misfit in Implant-Supported Restorations: A Retrospective Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Automated Classification of Maxillary Sinus Ostium Patency Using a ConvNeXt-Tiny + DeiT Gated MLP-Based Hybrid Deep Learning Model: A Retrospective CBCT Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Automated Early Detection of Skin Cancer Using a CNN-ViT-Attention-Based Hybrid Model.

Biomedicines·2026
Same author

MidFusionEfficientV2: Improving Ophthalmic Diagnosis with Mid-Level RGB-LBP Fusion and SE Attention.

Journal of clinical medicine·2026
Same author

Evaluation of Maxillary Sinus Membrane Morphology Using a Novel Hybrid CNN-ViT-Based Deep Learning Model: An Automated Classification Study.

Diagnostics (Basel, Switzerland)·2026

This study introduces a hybrid 3D U-Net and extreme learning machine (ELM) model for efficient and accurate liver segmentation in CT scans, offering a computationally lighter alternative for medical imaging analysis.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Anatomy

Background:

  • Accurate liver segmentation is crucial for surgical planning, volumetric analysis, and tumor assessment in abdominal CT images.
  • Deep learning models offer high segmentation performance but demand significant computational resources and training time.

Purpose of the Study:

  • To develop a computationally efficient hybrid framework for liver segmentation using 3D U-Net and extreme learning machine (ELM).
  • To refine liver segmentation by combining deep volumetric features from 3D U-Net with ELM classification.

Main Methods:

  • A hybrid framework integrating 3D U-Net for feature extraction and ELM for segmentation refinement was proposed.
  • Experiments were conducted on the Task03_Liver_rs dataset with fivefold cross-validation.
Keywords:
3D U-Netcomputed tomography (CT)extreme learning machine (ELM)hybrid deep learningliver segmentationmedical image segmentation

Related Experiment Videos

Last Updated: Jun 27, 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

  • Evaluation included overlap-based, boundary-based (HD95, ASD, surface Dice), and volumetric error metrics.

    • Main Results:

    • The 3D U-Net-ELM framework achieved competitive segmentation performance, with a mean Dice score of 0.9399 and IoU of 0.8874.
    • The model demonstrated improved boundary consistency and volumetric accuracy, evidenced by lower HD95 and ASD values.
    • The hybrid approach offered enhanced computational efficiency and reduced training costs compared to other models.

    Conclusions:

    • The 3D U-Net-ELM framework presents a balanced and computationally efficient solution for volumetric liver segmentation.
    • Further validation on diverse, multicenter datasets is needed to confirm clinical applicability and generalizability.