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

Kynurenic acid mediates epicardial fat-induced lymphatic metabolic dysfunction in atrial fibrillation.

Nature communications·2026
Same author

Vesicular nucleotide transporter (VNUT)-dependent ATP secretion by hepatic stellate cells promotes liver fibrosis.

Biochimica et biophysica acta. Molecular basis of disease·2026
Same author

Effects of <i>Orthonairovirus hazaraense</i> Nucleoprotein on Gene Expression Profiles in Infected Cells.

Viruses·2026
Same author

Membranous remodeling of basal infoldings in attenuated epithelial cells of dilated renal tubules under unilateral ureteral obstruction (UUO) in adult mouse kidney.

Histology and histopathology·2026
Same author

Three-Dimensional Ultrastructural Characterization of Fibroblastic/Stromal Cell Processes in Mouse Ureteral Lamina Propria by FE-SEM Array Tomography.

Microscopy research and technique·2025
Same author

Papillary muscle 18F-fluorodeoxyglucose uptake in heart failure with recovered ejection fraction: reversible metabolic remodelling mimicking cardiac sarcoidosis.

European heart journal·2025

Related Experiment Video

Updated: Oct 29, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K

Reducing manual operation time to obtain a segmentation learning model for volume electron microscopy using stepwise

Kohki Konishi1, Takao Nonaka2, Shunsuke Takei

  • 1Research and Development Division, Nikon Corporation, 471, Nagaodai, Sakae, Yokohama, Kanagawa 244-8533, Japan.

Microscopy (Oxford, England)
|July 14, 2021
PubMed
Summary

This study introduces a new tool for 3D deep learning (DL) organelle segmentation. The stepwise annotation method significantly reduces manual effort and time, improving segmentation efficiency.

Keywords:
deep convolutional neural networkelectron microscopy image stackimage segmentationmachine learningmouse cerebral cortex

More Related Videos

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

10.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.7K

Related Experiment Videos

Last Updated: Oct 29, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

10.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.7K

Area of Science:

  • Cell Biology
  • Neuroscience
  • Computational Biology

Background:

  • Serial-section electron microscopy enables 3D biological sample observation.
  • Manual organelle segmentation is time-consuming and labor-intensive.
  • 3D deep learning (DL) offers high accuracy but requires extensive training data.

Purpose of the Study:

  • To develop an efficient integrated tool for 3D organelle segmentation.
  • To reduce manual time and effort in creating training data for 3D DL models.
  • To improve the overall efficiency of organelle segmentation in biological samples.

Main Methods:

  • Development of an integrated image segmentation tool with efficient tracers, a lightweight convolutional neural network for DL model training/inference, and proofreading/refinement functions.
  • Application of a stepwise annotation method to incrementally increase training data.
  • Segmentation of mitochondria in cerebral cortex cells using the developed tool and method.

Main Results:

  • The stepwise annotation method reduced manual operation time by one-third compared to fully manual annotation.
  • A 3D DL model trained with stepwise annotation achieved an F1 score of 0.9 for segmentation accuracy.
  • The developed tool and stepwise annotation method demonstrated improved segmentation efficiency for various organelles.

Conclusions:

  • The integrated tool and stepwise annotation method significantly enhance the efficiency of 3D organelle segmentation.
  • This approach addresses the bottleneck of manual training data creation for 3D DL in biological imaging.
  • The findings are applicable to improving the analysis of complex biological structures using 3D electron microscopy.