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

Rejuvenation of corticospinal neurons enhances rehabilitation-associated corticospinal tract axon sprouting and functional recovery post photothrombotic ischemic stroke in mice.

Genes & diseases·2026
Same author

Zingerone alleviates acute seizures by reducing intrinsic hippocampal neuronal excitability in a rat model of temporal lobe epilepsy.

Frontiers in neuroscience·2026
Same author

Author Correction: Projectome-based characterization of hypothalamic peptidergic neurons in male mice.

Nature neuroscience·2025
Same author

Molecularly defined cellular atlas of the entire mouse brain with isotropic single-cell resolution.

Nature communications·2025
Same author

TNEA Regulates Hippocampal Oscillation by Improving Inhibitory Synaptic Plasticity to Ameliorates Cognitive Impairment in Alzheimer's Disease.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Lower FT3 levels are associated with a poor prognosis in patients with acute type A aortic dissection: a retrospective study.

European journal of medical research·2025

Related Experiment Video

Updated: Dec 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

DeepMapi: a Fully Automatic Registration Method for Mesoscopic Optical Brain Images Using Convolutional Neural

Hong Ni1, Zhao Feng1, Yue Guan1

  • 1Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, MoE Key Laboratory for Biomedical Photonics, School of Engineering Sciences, Huazhong University of Science and Technology, Wuhan, China.

Neuroinformatics
|August 6, 2020
PubMed
Summary
This summary is machine-generated.

DeepMapi, a novel deep learning method, enables automatic registration of mesoscopic brain images to atlases. This advancement significantly improves the efficiency and accuracy of neuroanatomical structure mapping.

Keywords:
Brain image registrationConvolutional neural networksDeep learningMesoscopic optical images

More Related Videos

A Large Lateral Craniotomy Procedure for Mesoscale Wide-field Optical Imaging of Brain Activity
10:05

A Large Lateral Craniotomy Procedure for Mesoscale Wide-field Optical Imaging of Brain Activity

Published on: May 7, 2017

12.7K
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

43.3K

Related Experiment Videos

Last Updated: Dec 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K
A Large Lateral Craniotomy Procedure for Mesoscale Wide-field Optical Imaging of Brain Activity
10:05

A Large Lateral Craniotomy Procedure for Mesoscale Wide-field Optical Imaging of Brain Activity

Published on: May 7, 2017

12.7K
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

43.3K

Area of Science:

  • Neuroscience
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Mammalian brain complexity necessitates detailed neuroanatomical mapping using stereotactic atlases.
  • Image registration is challenging due to variations in resolution, dataset size, and inherent misalignment, hindering high-throughput analysis.
  • Current methods often require manual intervention, limiting efficiency in processing mesoscopic imaging data.

Purpose of the Study:

  • To develop a deep learning-based method, DeepMapi, for automatic registration of mesoscopic optical brain images to a stereotactic atlas.
  • To overcome limitations of existing registration techniques, including imbalanced training data and the need for manual input.
  • To achieve accurate and efficient mapping of neuronal structures in large-scale brain imaging datasets.

Main Methods:

  • Proposed DeepMapi, a deep learning model predicting deformation fields for image registration.
  • Implemented a self-feedback strategy to manage imbalanced training datasets with non-uniform structures and deformations.
  • Utilized a dual-hierarchical network architecture to effectively capture both large and small deformations within brain images.

Main Results:

  • DeepMapi demonstrated superior performance compared to existing registration methods on ground truth datasets, including optical and MRI images.
  • Achieved fully automatic registration of mesoscopic optical and macroscopic MRI brain datasets within minutes.
  • Registration accuracy was comparable to manual annotations provided by expert anatomists.

Conclusions:

  • DeepMapi offers a robust, fully automatic solution for registering mesoscopic brain images to atlases.
  • The method significantly enhances the speed and accuracy of neuroanatomical analysis, facilitating large-scale brain research.
  • DeepMapi's performance suggests its potential to become a standard tool in neuroscience and medical imaging analysis.