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 Experiment Video

Updated: Sep 5, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.2K

Evaluation of Image Classification for Quantifying Mitochondrial Morphology Using Deep Learning.

Kaori Tsutsumi1, Keima Tokunaga2, Shun Saito3

  • 1Faculty of Health Sciences, Hokkaido University, Sapporo, Japan.

Endocrine, Metabolic & Immune Disorders Drug Targets
|July 5, 2022
PubMed
Summary

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

Real-world evaluation of primary prophylactic use of granulocyte colony-stimulating factor in patients with metastatic castration-sensitive prostate cancer treated with triplet therapy.

International journal of clinical oncology·2026
Same author

Activation of hamiformamide production in the thermotolerant fungus Hamigera avellanea triggered by co-culture with animal immune cells.

The Journal of antibiotics·2026
Same author

Surgical Video Understanding with Alignment-Preserving Temporal Adaptation and Action Triplet Text Alignment.

Bioengineering (Basel, Switzerland)·2026
Same author

Densely Packed and Well-Aligned Liquid-Crystalline Scaffolds Drive Controllable Axial Crystal Strain.

Journal of the American Chemical Society·2026
Same author

Catenulamide A, an acylated tripeptide containing 5-methoxy-L-kynurenine lactam from an actinomycete of the genus Catenuloplanes.

The Journal of antibiotics·2026
Same author

Spatiotemporal dynamics and ossification of podoplanin-positive cells in the developing femur.

Scientific reports·2026

This study developed a Deep Learning classifier to objectively categorize mitochondrial morphology, a key indicator of cell state and fate. The AI model achieved high accuracy in distinguishing between fission and fusion patterns in cells.

Area of Science:

  • Cell Biology
  • Biotechnology
  • Artificial Intelligence

Background:

  • Mitochondrial morphology, involving fission and fusion, reflects cellular condition and predicts cell fate.
  • Current methods for classifying mitochondrial dynamics are subjective and lack objectivity.
  • Mitochondrial dynamics serve as a simple indicator of cell state.

Purpose of the Study:

  • To evaluate the efficacy of Deep Learning (DL) techniques for classifying mitochondrial morphology.
  • To develop an objective and automated method for assessing mitochondrial dynamics.
  • To correlate mitochondrial morphology with cellular condition and fate prediction.

Main Methods:

  • Mitochondrial images were acquired from HeLa and MC3T3-E1 cells using fluorescent microscopy.
Keywords:
Mitochondrial morphologyResNetdeep learningfissionfusionmitochondrial dynamics

More Related Videos

Determination of Mitochondrial Morphology in Live Cells Using Confocal Microscopy
06:57

Determination of Mitochondrial Morphology in Live Cells Using Confocal Microscopy

Published on: July 3, 2025

290
Understanding the Changes in Mitochondrial Morphology through Dynamic and Three-dimensional Fluorescence Micrographs
08:15

Understanding the Changes in Mitochondrial Morphology through Dynamic and Three-dimensional Fluorescence Micrographs

Published on: August 15, 2025

69

Related Experiment Videos

Last Updated: Sep 5, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.2K
Determination of Mitochondrial Morphology in Live Cells Using Confocal Microscopy
06:57

Determination of Mitochondrial Morphology in Live Cells Using Confocal Microscopy

Published on: July 3, 2025

290
Understanding the Changes in Mitochondrial Morphology through Dynamic and Three-dimensional Fluorescence Micrographs
08:15

Understanding the Changes in Mitochondrial Morphology through Dynamic and Three-dimensional Fluorescence Micrographs

Published on: August 15, 2025

69
  • Images were classified into four groups based on fission or fusion, with excellent inter-rater reliability.
  • A 50-layer ResNet Convolutional Neural Network (CNN) architecture was trained using MATLAB with five-fold cross-validation.

    • Main Results:

    • The DL classifier achieved a mean overall accuracy of 0.73±0.10 for classifying mitochondrial morphology in HeLa cells.
    • Training with mixed cell line images improved classification accuracy (0.74±0.01) compared to single cell line training.
    • The developed classifier demonstrated robust performance in categorizing mitochondrial morphology.

    Conclusions:

    • A Deep Learning-based classifier was successfully developed to categorize mitochondrial morphology.
    • This AI approach offers an objective method for analyzing mitochondrial dynamics.
    • The findings suggest DL can be a valuable tool in cell biology research for assessing cell state and fate.