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

Diffusion MRI of the Body: Beyond PGSE-EPI.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Radiofrequency electrical conductivity reveals a distinct dimension of early human brain development.

Scientific reports·2026
Same author

Real-Time Targeted Slice Reacquisition for Motion-Corrupted Fetal Diffusion MRI.

Magnetic resonance in medicine·2026
Same author

Normative volumetric growth modeling of the whole fetal body, placenta, and amniotic fluid for three-dimensional T2-weighted magnetic resonance imaging.

Pediatric radiology·2026
Same author

Neonatal brain structure, cognitively stimulating parenting and behavioural outcomes in preschool children with congenital heart disease and controls.

Scientific reports·2026
Same author

Prenatal air pollution exposure is associated with altered neurodevelopmental outcomes in early childhood.

The Journal of physiology·2026

Related Experiment Video

Updated: Oct 17, 2025

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

1.4K

dStripe: Slice artefact correction in diffusion MRI via constrained neural network.

Maximilian Pietsch1, Daan Christiaens2, Joseph V Hajnal3

  • 1Centre for Medical Engineering, King's College London, London, UK; Centre for the Developing Brain, King's College London, London, UK; Department of Forensic & Neurodevelopmental Sciences, King's College London, London, UK.

Medical Image Analysis
|October 11, 2021
PubMed
Summary

This study introduces a novel deep learning method to correct inter-slice intensity variations in Echo Planar Imaging (EPI) data. The technique effectively reduces motion and dropout artifacts, improving image quality for diffusion imaging.

Keywords:
Diffusion MRIImage artefact removalVenetian blind artefact

More Related Videos

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.7K
Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury
10:33

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

8.7K

Related Experiment Videos

Last Updated: Oct 17, 2025

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

1.4K
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.7K
Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury
10:33

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

8.7K

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Neuroimaging

Background:

  • Echo Planar Imaging (EPI) is susceptible to inter-slice intensity variations due to scanner imperfections and motion.
  • These variations can manifest as acquisition artifacts, impacting image quality and data analysis.
  • Existing reconstruction techniques struggle to fully address these inconsistencies.

Purpose of the Study:

  • To develop a data-driven deep learning method for correcting inter-slice intensity inconsistencies in EPI data.
  • To address acquisition artifacts, including motion and dropout, regardless of their origin.
  • To enhance the reconstruction of diffusion imaging data, particularly for neonatal studies.

Main Methods:

  • Leveraged deep convolutional neural networks as universal image filters for artifact correction.
  • Trained the network in the absence of ground-truth data, applying it to reconstructed multi-shell high angular resolution diffusion imaging (HARDI) data.
  • Developed a corrective slice intensity modulation field, applicable in motion-corrected or scattered source-space.
  • Incorporated spatial frequency and intensity constraints to control the learned filter and ensure image data consistency.

Main Results:

  • The method produces a corrected image by modulating the original raw data with a verifiable multiplicative field.
  • Correction preserves in-plane diffusion signal contrast and reduces inter-slice inconsistencies across subjects.
  • The pipeline enhances super-resolution reconstruction of neonatal multi-shell HARDI data without biasing the data.

Conclusions:

  • The presented deep learning approach effectively corrects EPI inter-slice intensity variations and acquisition artifacts.
  • This technique offers a robust solution for improving image quality in diffusion MRI, especially for challenging datasets like neonatal data.
  • The method provides a reliable tool for enhancing neuroimaging analysis by ensuring data consistency.