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 26, 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

Hybrid Neural Network Architecture for Automated Liver and Tumor Segmentation Using Ensemble Learning on CT Images.

Maryam Khoshkhabar1, Saeed Meshgini1, Reza Afrouzian1

  • 1Department of Biomedical Engineering, University of Tabriz, Tabriz 5166616471, Iran.

Biomimetics (Basel, Switzerland)
|June 25, 2026
PubMed
Summary
This summary is machine-generated.

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

Deep Learning-Based Automatic Segmentation of Ischemic Stroke Lesions in CT Perfusion Imaging.

Biomimetics (Basel, Switzerland)·2026
Same author

Investigating time distortion in Parkinson's disease considering impaired frontoparietal network and changes in the brain dynamic.

Biomedical physics & engineering express·2026
Same author

Neonatal seizure detection from EEG using inception ResNetV2 feature extraction and XGBoost optimized with particle swarm optimization.

Scientific reports·2025
Same author

Enhanced Brain Stroke Lesion Segmentation in MRI Using a 2.5D Transformer Backbone U-Net Model.

Brain sciences·2025
Same author

Improved Automatic Deep Model for Automatic Detection of Movement Intention from EEG Signals.

Biomimetics (Basel, Switzerland)·2025
Same author

Estimating mandibular growth stage based on cervical vertebral maturation in lateral cephalometric radiographs using artificial intelligence.

Progress in orthodontics·2024

This study introduces a novel hybrid ensemble neural network for accurate liver and liver tumor segmentation in CT scans. The model achieves high accuracy and robust performance, even with noisy images, improving computer-assisted diagnosis.

Area of Science:

  • Medical Image Analysis
  • Artificial Intelligence in Radiology
  • Computational Pathology

Background:

  • Deep learning models like U-Net excel at medical image segmentation but struggle with long-range spatial relationships and noisy CT data.
  • Accurate liver and liver tumor segmentation is crucial for diagnosis, treatment planning, and clinical decisions.
  • Challenges include low contrast, irregular boundaries, and artifacts in CT images.

Purpose of the Study:

  • To develop a hybrid ensemble neural network for accurate and robust automatic segmentation of the liver and liver tumors in CT images.
  • To address the limitations of existing models in capturing long-range spatial dependencies and handling noisy imaging conditions.

Main Methods:

  • A hybrid ensemble architecture combining an improved U-Net for local feature extraction and a Graph U-Net for modeling spatial relationships using SLIC superpixels.
Keywords:
biological systems inspirationbiomimetic systemsensemble architecturehybrid neural networkliver tumor detection

Related Experiment Videos

Last Updated: Jun 26, 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

  • Ensemble learning strategy to integrate complementary features from both networks.
  • Preprocessing of CT images including intensity filtering, resizing, data augmentation, and normalization on the LiTS17 dataset.

    • Main Results:

    • Achieved 99.2% accuracy for liver segmentation and 98.1% for liver tumor segmentation on the LiTS17 dataset.
    • Outperformed existing models like MultiresUnet and R2U-Net.
    • Demonstrated robust performance in noisy conditions, maintaining 85% accuracy at -4 dB SNR, highlighting improved stability.

    Conclusions:

    • The proposed hybrid ensemble network effectively integrates convolutional and graph-based modeling for accurate and noise-robust liver and liver tumor segmentation.
    • The approach shows significant potential as a computer-assisted tool for clinical image analysis, particularly in challenging imaging scenarios.
    • Further validation on larger datasets is recommended to confirm clinical applicability.