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

Prediction of Infant MRI Appearance and Anatomical Structure Evolution using Sparse Patch-based Metamorphosis

Islem Rekik1, Gang Li1, Guorong Wu1

  • 1Department of Radiology and BRIC, University of North Carolina at Chapel Hill, NC, USA.

Patch-Based Techniques in Medical Imaging : First International Workshop, Patch-Mi 2015, Held in Conjunction with MICCAI 2015, Munich, Germany, October 9, 2015, Revised Selected Papers. Patch-Mi (Workshop) (1St : 2015 : Munich, Germany)
|April 11, 2017
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

Denoising Diffusion-Weighted Images Using Grouped Iterative Hard Thresholding of Multi-Channel Framelets.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Construction of Diffusion MRI Atlases with Correction for Inter-Subject Fiber Dispersion.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Fusion of Diffusion MRI Data for Template Construction.

Scientific reports·2017
Same author

Learning-Based Multimodal Image Registration for Prostate Cancer Radiation Therapy.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2017
Same author

Segmenting hippocampal subfields from 3T MRI with multi-modality images.

Medical image analysis·2017
Same author

Joint Discriminative and Representative Feature Selection for Alzheimer's Disease Diagnosis.

Machine learning in medical imaging. MLMI (Workshop)·2017

Predicting infant brain development using magnetic resonance imaging (MRI) is challenging. This study introduces a novel framework to forecast brain image evolution, showing promising results for predicting future brain structure and intensity in infants.

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Developmental Neuroscience

Background:

  • Pediatric brain magnetic resonance imaging (MRI) is crucial for understanding early brain development, both normal and abnormal.
  • Longitudinal neuroimaging studies have explored infant brain development patterns, but predicting postnatal brain image evolution remains a significant challenge due to dynamic tissue contrast changes.

Purpose of the Study:

  • To develop and validate a novel framework for predicting postnatal brain MRI evolution, specifically focusing on image intensity and anatomical structure.
  • To address the scarcity of studies predicting dynamic changes in infant brain development using neuroimaging.

Main Methods:

  • A dual image intensity and anatomical structure prediction framework was proposed, integrating a geodesic image metamorphosis model with sparse patch-based image representation.

Related Experiment Videos

  • This framework defines spatiotemporal metamorphic patches encoding both photometric and geometric deformation, learning 4D metamorphosis trajectories during training.
  • In the prediction stage, testing image patches are sparsely represented using training metamorphosis patches, with strategies ranging from appearance-based to multimodal kinetic patches.

    • Main Results:

    • The framework was used to predict 6, 9, and 12-month brain MR image intensity and structure (white and gray matter maps) from 3-month-old infant data.
    • Promising preliminary prediction results were achieved for the complex and rapidly changing spatiotemporal characteristics of infant brain images.
    • The study demonstrated the feasibility of predicting longitudinal changes in brain morphology and tissue composition.

    Conclusions:

    • The proposed dual prediction framework offers a novel approach to forecasting infant brain development from MRI data.
    • This method shows potential for advancing our understanding of early neurodevelopmental trajectories and identifying deviations.
    • Further research is warranted to refine the prediction accuracy and explore clinical applications for early diagnosis.