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

Intrinsic elaboration of prefrontal modularity: a dual-control model of axon bundling and synaptic docking.

Frontiers in neuroanatomy·2026
Same author

Memory efficient training for 3D brain image registration networks using PatchMorph.

Scientific reports·2026
Same author

An evolutionary view on the developing prefrontal cortex connectome and its psychopathological networks: Tract tracing and imaging studies linking two distant anthropoid species.

Research square·2026
Same author

Multimodal Machine Learning Approach for Diagnosing Atopic Dermatitis.

F1000Research·2026
Same author

Complexity-based EEG biomarkers for early diagnosis of ADHD.

International journal of psychophysiology : official journal of the International Organization of Psychophysiology·2026
Same author

Development and usability testing of a depth camera-based web application for functionally relevant foot kinematics analysis.

Frontiers in medical technology·2025

Related Experiment Video

Updated: Jul 13, 2025

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

48.1K

Exploring the performance of implicit neural representations for brain image registration.

Michal Byra1,2, Charissa Poon3, Muhammad Febrian Rachmadi3,4

  • 1RIKEN Center for Brain Science, Wako, Japan. michal.byra@riken.jp.

Scientific Reports
|October 13, 2023
PubMed
Summary

Implicit neural representations (INRs) enhance brain image registration accuracy in MRI. Exploring diverse activation functions and advanced techniques, these methods show strong potential for neuroscience and radiology applications.

More Related Videos

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

42.7K
Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

780

Related Experiment Videos

Last Updated: Jul 13, 2025

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

48.1K
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

42.7K
Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

780

Area of Science:

  • Medical Imaging
  • Computational Neuroscience
  • Machine Learning

Background:

  • Pairwise image registration is crucial for comparing and integrating brain imaging data in neuroscience and radiology.
  • Implicit Neural Representations (INRs) offer a continuous, coordinate-based approach to modeling deformation fields.

Purpose of the Study:

  • To evaluate the effectiveness of INRs for improving magnetic resonance imaging (MRI) brain image registration.
  • To explore various activation functions and optimization techniques to enhance INR performance.

Main Methods:

  • Investigated diverse activation functions (SIRENs, ReLU, snake, sine+, chirp, Morlet wavelet) within INRs.
  • Related model hyperparameters to registration performance.
  • Assessed techniques like cycle consistency loss, ensembles, cascades, and combined objectives.
  • Compared INR methods against VoxelMorph and ANTs' SyN algorithm.

Main Results:

  • Implicit networks demonstrate significant capabilities in pairwise brain image registration.
  • Tested activation functions and optimization strategies showed varied impacts on performance.
  • INR methods achieved competitive or superior results compared to established algorithms.

Conclusions:

  • INRs show remarkable potential for addressing pairwise image registration challenges in neuroimaging.
  • Implicit networks offer a versatile, off-the-shelf tool for neuroscience and radiology.