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

DDEvENet: Evidence-based ensemble learning for uncertainty-aware brain parcellation using diffusion MRI.

Chenjun Li1, Dian Yang1, Shun Yao2

  • 1University of Electronic Science and Technology of China, Chengdu, Sichuan, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|January 9, 2025
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

Correction: Proximity proteomics reveals OTUD6B regulation of stress granule dynamics through coalescence with VCP/p97.

Cell death & disease·2026
Same author

TractoMFormer: A novel streamline-level tractography analysis framework for group classification using deep graph and multi-scale ViT.

NeuroImage·2026
Same author

<i>Alfaria yunnanensis</i> sp. nov., a novel myrothecium-like species isolated from <i>Oryza sativa</i> in Yunnan, China.

International journal of systematic and evolutionary microbiology·2026
Same author

Composition-dependent synergistic effects of elements on elastic properties in the MoNbTaVW-series refractory high-entropy alloys.

Journal of molecular modeling·2026
Same author

Study of sex differences in the whole brain white matter using diffusion MRI tractography and suprathreshold fiber cluster statistics.

NeuroImage. Clinical·2026
Same author

On the consistent and scalable detection of spatial patterns.

ArXiv·2026
Same journal

RGCNN-nnUNet: Recurrent group equivariant nnU-Net for robust brain tissue segmentation on stroke NCCT.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
See all related articles
This summary is machine-generated.

We developed DDEvENet, a deep learning model using diffusion MRI for brain parcellation. It accurately maps brain anatomy and quantifies uncertainty, improving segmentation reliability for various conditions.

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Medical Image Analysis

Background:

  • Accurate anatomical brain parcellation is crucial for understanding brain structure and function.
  • Existing methods often struggle with variability in diffusion MRI (dMRI) data and lack robust uncertainty quantification.
  • Deep learning offers potential but requires careful handling of uncertainty in clinical applications.

Purpose of the Study:

  • To introduce DDEvENet, an Evidential Ensemble Neural Network for precise anatomical brain parcellation using dMRI.
  • To develop a framework for quantifying voxel-wise predictive uncertainty during inference.
  • To leverage multiple dMRI parameters within an uncertainty-aware ensemble learning approach.

Main Methods:

  • Developed DDEvENet, an evidential deep learning framework integrating multiple parallel subnetworks, each processing a specific dMRI parameter.
Keywords:
Brain parcellationDeep learningDiffusion MRIUncertainty estimation

Related Experiment Videos

  • Implemented an evidence-based ensemble methodology to fuse outputs from individual subnetworks.
  • Trained and evaluated the network on diverse dMRI datasets from healthy controls and patients with various neurological and psychiatric disorders.

    • Main Results:

    • DDEvENet achieved highly improved parcellation accuracy across multiple datasets, outperforming state-of-the-art methods.
    • The model provided reliable voxel-wise uncertainty estimates, aiding in the detection of abnormal brain regions.
    • Results demonstrated robustness across different dMRI acquisition protocols and patient populations.

    Conclusions:

    • DDEvENet offers an accurate and reliable method for anatomical brain parcellation using dMRI.
    • The integrated uncertainty quantification enhances interpretability and aids in identifying pathological brain changes.
    • This approach holds significant potential for clinical neuroimaging research and diagnostics.