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

Calcium/calmodulin-dependent protein kinase II links ER stress with Fas and mitochondrial apoptosis pathways.

The Journal of clinical investigation·2009
Same author

Cripto-1 overexpression is involved in the tumorigenesis of nasopharyngeal carcinoma.

BMC cancer·2009
Same author

Range of motion and orientation of the lumbar facet joints in vivo.

Spine·2009
Same author

[Silencing of COX-2 in nasopharyngeal carcinoma cells with a shRNAmir lentivirus vector].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2009
Same author

The risk of melamine-induced nephrolithiasis in young children starts at a lower intake level than recommended by the WHO.

Pediatric nephrology (Berlin, Germany)·2009
Same author

Adult scoliosis in patients over sixty-five years of age: outcomes of operative versus nonoperative treatment at a minimum two-year follow-up.

Spine·2009

Related Experiment Video

Updated: Sep 1, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.8K

Harmonized neonatal brain MR image segmentation model for cross-site datasets.

Jian Chen1,2, Yue Sun2, Zhenghan Fang2

  • 1School of Electronic, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou, Fujian, China.

Biomedical Signal Processing and Control
|August 15, 2022
PubMed
Summary

This study introduces a novel method for segmenting neonatal brain MR images, improving accuracy across different scanners and reducing artifacts. The approach harmonizes images, enabling robust segmentation for better early brain development characterization.

Keywords:
ArtifactsCross-site datasetsCross-timeCycleGANNeonatal brainSegmentation

More Related Videos

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K

Related Experiment Videos

Last Updated: Sep 1, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.8K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Accurate segmentation of neonatal brain MRI is crucial for understanding early brain development.
  • Deep learning models for MRI segmentation perform poorly on data from different scanners or protocols.
  • Imaging artifacts, such as head motion, further challenge segmentation accuracy.

Purpose of the Study:

  • To develop a robust neonatal brain MR image segmentation model that overcomes variations in imaging protocols and scanners.
  • To address the challenge of imaging artifacts in neonatal brain MRIs.
  • To improve the characterization of early brain development through enhanced segmentation.

Main Methods:

  • A CycleGAN-based model was developed to harmonize neonatal brain MR images from different sources, aligning them to a common domain.
  • The harmonization process also served to alleviate common imaging artifacts.
  • A densely-connected U-Net segmentation model was trained on harmonized images for robust performance.

Main Results:

  • The proposed harmonized segmentation model demonstrated superior performance on cross-site neonatal brain MR images compared to existing methods.
  • The method effectively handled images with significant artifacts, improving segmentation quality.
  • Successful harmonization led to more accurate segmentation of white matter, gray matter, and cerebrospinal fluid.

Conclusions:

  • The CycleGAN-based harmonization approach enables robust neonatal brain MR image segmentation across different sites and protocols.
  • This method significantly improves segmentation accuracy and artifact reduction, aiding in the study of early brain development.
  • The proposed model offers a promising solution for standardized and reliable neonatal brain image analysis.