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 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

Related Experiment Video

Updated: Feb 23, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.6K

Learning-based deformable registration for infant MRI by integrating random forest with auto-context model.

Lifang Wei1,2, Xiaohuan Cao3,2, Zhensong Wang4,2

  • 1College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou, 350002, China.

Medical Physics
|September 14, 2017
PubMed
Summary

This study introduces a novel learning-based method for infant brain MRI registration, accurately analyzing rapid structural changes in the first year of life. The approach effectively handles anatomical and appearance variations, improving early brain development research.

Keywords:
auto-context modeldeformable image registrationinfant brain MRIrandom forest regression

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.6K

Related Experiment Videos

Last Updated: Feb 23, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.6K

Area of Science:

  • Neuroimaging
  • Developmental Neuroscience
  • Medical Image Analysis

Background:

  • Accurate analysis of rapid human brain structural evolution in the first year of life is crucial for early brain development studies.
  • Existing deformable image registration methods struggle with dynamic appearance and large anatomical changes in infant brain MR images.

Purpose of the Study:

  • To develop a robust learning-based registration method for infant brain MR images acquired at different developmental stages.
  • To address challenges of dynamic appearance and significant anatomical changes in infant brain registration.

Main Methods:

  • A learning-based approach utilizing multi-output random forest regression and an auto-context model trained on longitudinal infant MRI data.
  • Harnessing multimodal MRI information to enhance the robustness of the learning procedure.
  • Predicting deformation fields and appearance changes for new infant images during the testing phase.

Main Results:

  • The proposed method achieved promising registration accuracy in intersubject registration of infant brain MR images from 2 weeks to 12 months old.
  • Demonstrated superior performance compared to non-learning-based registration methods.

Conclusions:

  • The developed learning-based registration method effectively addresses challenges in registering infant brain images within the first year of life.
  • The method leverages advanced machine learning models to learn shape and appearance evolution, enabling accurate prediction of deformation and appearance for new images.
  • Achieved higher accuracy than state-of-the-art deformable registration methods, particularly in cases with substantial appearance and shape changes.