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 Videos

Spatial Evidential Clustering With Adaptive Distance Metric for Tumor Segmentation in FDG-PET Images.

Chunfeng Lian, Su Ruan, Thierry Denoux

    IEEE Transactions on Bio-Medical Engineering
    |April 4, 2017
    PubMed
    Summary

    This study introduces a novel Dempster-Shafer theory-based clustering algorithm to improve tumor segmentation in FDG-PET images. The method enhances accuracy by addressing noise and imprecision, leading to better tumor volume delineation.

    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

    Generative restoration for cardiac PET attenuation correction: a two-stage 3D DDIM framework optimizing fidelity and clinical controllability.

    EJNMMI physics·2026
    Same author

    Model-unrolled fast MRI with weakly supervised lesion enhancement.

    Medical image analysis·2025
    Same author

    Collaborative and privacy-preserving cross-vendor united diagnostic imaging via server-rotating federated machine learning.

    Communications engineering·2025
    Same author

    Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning.

    Nature communications·2025
    Same author

    Anatomy-Aware Deep Unrolling for Task-Oriented Acceleration of Multi-Contrast MRI.

    IEEE transactions on medical imaging·2025
    Same author

    Explainable AI for sharp injury identification using transfer learning with pre-trained deep neural networks.

    Forensic science international·2025

    Area of Science:

    • Medical Imaging
    • Computational Oncology
    • Artificial Intelligence

    Background:

    • Accurate tumor volume delineation in FDG-PET is crucial for clinical oncology.
    • Image noise and blur in PET scans present significant challenges for precise segmentation.
    • Existing methods struggle with the inherent uncertainty and imprecision of PET data.

    Purpose of the Study:

    • To develop a novel evidential clustering algorithm for 3D tumor segmentation in FDG-PET images.
    • To address the challenges of noise and imprecision in PET imaging using Dempster-Shafer theory.
    • To improve the accuracy of tumor volume delineation in clinical oncology.

    Main Methods:

    • A novel evidential clustering algorithm based on Dempster-Shafer theory was developed for 3D PET tumor segmentation.

    Related Experiment Videos

  • Voxels were characterized by intensity and textural features, with an adaptive distance metric to handle unreliable data.
  • Dempster-Shafer-theory-based spatial regularization was incorporated to quantify local homogeneity.

    • Main Results:

    • The proposed algorithm demonstrated good performance in segmenting tumors in real-patient FDG-PET images.
    • The method effectively addressed noise and imprecision inherent in PET data.
    • Feature selection and metric adaptation improved the robustness of the clustering.

    Conclusions:

    • The Dempster-Shafer theory-based evidential clustering offers a promising approach for accurate tumor segmentation in FDG-PET imaging.
    • The integrated metric adaptation and spatial regularization enhance segmentation quality.
    • This method has the potential to improve clinical oncology outcomes through better tumor volume delineation.