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

A quantitative and precision‑oriented neuronal reconstruction approach based on data grading.

Brain informatics·2026
Same author

A Million-Scale, Difficulty-Stratified Optical-Microscopy Image Annotation for Neuron Reconstruction.

Scientific data·2026
Same author

Femtosecond laser-assisted cataract surgery versus conventional phacoemulsification surgery: visual outcomes with presbyopia-correcting intraocular lens.

Frontiers in medicine·2026
Same author

Polydeoxyribonucleotide improves scar healing following limited scar resection for chronic Achilles tendon rupture in a rat model.

Journal of orthopaedic surgery and research·2026
Same author

Brain-SAM: a general automatic SAM-based segmentation model for brain science images.

Biomedical optics express·2026
Same author

Correction to: IGF-1 Provides Protective Role in Arteriosclerotic Cerebral Small Vessel Disease.

Hypertension (Dallas, Tex. : 1979)·2025

Related Experiment Video

Updated: Sep 29, 2025

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
08:49

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

3.8K

Deep residual contextual and subpixel convolution network for automated neuronal structure segmentation in

Chi Xiao1, Bei Hong2, Jing Liu2

  • 1Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, China; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China.

Computer Methods and Programs in Biomedicine
|March 26, 2022
PubMed
Summary

A novel deep learning method accurately segments neuronal structures in electron microscopy images, advancing micro-connectomics research. This approach aids neuroanatomists by automating segmentation and reconstruction, reducing manual effort.

Keywords:
Deep learningElectron microscopyMicro-ConnectomicsNeuronal structure segmentationSubpixel convolution

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.9K

Related Experiment Videos

Last Updated: Sep 29, 2025

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
08:49

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

3.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.9K

Area of Science:

  • Neuroscience
  • Computational Biology
  • Biomedical Imaging

Background:

  • Micro-connectomics aims to map neural connections using electron microscopy (EM).
  • Neuron segmentation is a critical yet challenging step in reconstructing neural circuits.
  • Manual segmentation is labor-intensive and requires expert neuroanatomists.

Purpose of the Study:

  • To develop an automated, reliable method for neuronal structure segmentation in EM image stacks.
  • To improve the efficiency and accuracy of connectome reconstruction.
  • To provide neuroanatomists with a tool to reduce manual labeling burdens.

Main Methods:

  • A deep learning approach utilizing a deep residual contextual and subpixel convolution network.
  • Application of lifted multicut for post-processing and optimization of segmentation predictions.
  • Validation on anisotropic EM image stacks and public datasets.

Main Results:

  • Achieved top ranking on the ISBI EM segmentation challenge with a Rand score of 0.98788.
  • Obtained high Rand scores (0.9562 and 0.9318) on mouse piriform cortex datasets.
  • Demonstrated significantly improved performance compared to existing state-of-the-art methods.

Conclusions:

  • The proposed deep learning method offers an effective solution for neuronal structure segmentation in micro-connectomics.
  • The automated approach enhances segmentation accuracy and aids in neuron reconstruction.
  • Contributes to the advancement of connectome research by providing a valuable tool for neuroanatomists.