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

Cadmium induced oxalic acid secretion and its role in metal uptake and detoxification mechanisms in Phanerochaete chrysosporium.

Applied microbiology and biotechnology·2014
Same author

[AS-PCR assay for 20 mtDNA SNP typing and haplotype frequency].

Fa yi xue za zhi·2014
Same author

Identification of ANKK1 rs1800497 variant in schizophrenia: new data and meta-analysis.

American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics·2014
Same author

Predictors of consistent condom use among Chinese female sex workers: an application of the protection motivation theory.

Health care for women international·2014
Same author

Overexpression of PEP-19 suppresses angiotensin II-induced cardiomyocyte hypertrophy.

Journal of pharmacological sciences·2014
Same author

Altered brain network modules induce helplessness in major depressive disorder.

Journal of affective disorders·2014

Related Experiment Video

Updated: Aug 20, 2025

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density
09:10

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

Published on: July 22, 2022

3.4K

Deep learning-based synapse counting and synaptic ultrastructure analysis of electron microscopy images.

Feng Su1, Mengping Wei2, Meng Sun2

  • 1Department of Neurobiology, School of Basic Medical Sciences, Beijing Key Laboratory of Neural Regeneration and Repair, Capital Medical University, Beijing 100069, China; Chinese Institute for Brain Research, Beijing 102206, China; State Key Laboratory of Translational Medicine and Innovative Drug Development, Nanjing 210000, Jiangsu, China; Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China.

Journal of Neuroscience Methods
|November 22, 2022
PubMed
Summary

This study introduces a deep learning system for analyzing synapses in electron microscopy images, improving efficiency and reducing bias in neurological research. The system accurately counts synapses and analyzes their ultrastructure, aiding in understanding brain function and disease.

Keywords:
Deep learningElectron microscopy imageSynaptic analysisSynaptic ultrastructure

More Related Videos

An Unbiased Approach of Sampling TEM Sections in Neuroscience
10:56

An Unbiased Approach of Sampling TEM Sections in Neuroscience

Published on: April 13, 2019

7.3K
Automated Quantification of Synaptic Fluorescence in C. elegans
12:22

Automated Quantification of Synaptic Fluorescence in C. elegans

Published on: August 10, 2012

10.4K

Related Experiment Videos

Last Updated: Aug 20, 2025

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density
09:10

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

Published on: July 22, 2022

3.4K
An Unbiased Approach of Sampling TEM Sections in Neuroscience
10:56

An Unbiased Approach of Sampling TEM Sections in Neuroscience

Published on: April 13, 2019

7.3K
Automated Quantification of Synaptic Fluorescence in C. elegans
12:22

Automated Quantification of Synaptic Fluorescence in C. elegans

Published on: August 10, 2012

10.4K

Area of Science:

  • Neuroscience
  • Computational Biology
  • Medical Imaging

Background:

  • Synapses are crucial for neuronal communication in the central and peripheral nervous systems.
  • Synaptic analysis is vital for understanding neurological functions and diseases.
  • Manual analysis of synaptic structures in electron microscopy (EM) images is inefficient and subjective.

Purpose of the Study:

  • To develop an automated, multifunctional system for synaptic analysis using deep learning.
  • To improve the efficiency and reduce bias in analyzing synaptic structures from EM images.

Main Methods:

  • Developed a system integrating multiple deep learning models for synaptic analysis.
  • Employed ResNet18 and Faster R-CNN for synapse counting (low-magnification EM images).
  • Utilized Faster R-CNN (ResNet50) and DeepLab v3+ (ResNet50) for synaptic ultrastructure analysis (high-magnification EM images).

Main Results:

  • Synapse counting achieved a mean average precision (mAP) of 92.55%.
  • Ultrastructure analysis demonstrated high performance: Faster R-CNN (ResNet50) achieved 91.60% mAP, and DeepLab v3+ achieved 0.9811 global accuracy for membrane segmentation.
  • Synaptic vesicle detection reached 91.41% mAP using Faster R-CNN (ResNet18).

Conclusions:

  • The developed deep learning system automates synaptic analysis from EM images.
  • This system offers a more objective and efficient alternative to manual analysis.
  • Facilitates advanced studies on synaptic function and neurological disorders.