Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 2, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Mitochondrial segmentation and function prediction in live-cell images with deep learning.

Yang Ding¹, Jintao Li¹, Jiaxin Zhang¹

¹Frontiers Science Center for Flexible Electronics, Xi'an Institute of Flexible Electronics (IFE) and Xi'an Institute of Biomedical Materials & Engineering, Northwestern Polytechnical University, Xi'an, China.

Nature Communications

|January 17, 2025

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

Micropillar-Based Biosensor for Monitoring Contamination- and Compound-Induced Metabolic States in Cell Cultures.

ACS applied materials & interfaces·2026

Same author

Chiral chromophore engineered donor for constructing circularly polarized organic long-persistent luminescence exciplex.

Nature communications·2026

Same author

Gradient-distributed metal-halide dynamic memristors for adaptive and robust voiceprint recognition.

Nature communications·2026

Same author

Interfacial Morphology Shapes Endothelial Organization and Function in a Blood-Brain Barrier-on-a-Chip.

ACS applied materials & interfaces·2026

Same author

Photocatalytic Activation of Alkyl Diazirine Probes for In Situ Drug Profiling and Extracellular Vesicle-Based Diagnostics.

Journal of the American Chemical Society·2026

Same author

Recent Advances of Organic Room Temperature Phosphorescence for Biological Applications.

Advanced materials (Deerfield Beach, Fla.)·2026

Summary

This summary is machine-generated.

A new deep learning algorithm, MoDL, accurately predicts mitochondrial function from live-cell images by analyzing morphology. This tool enhances mitochondrial research and drug discovery by linking form and function.

Area of Science:

Cell Biology
Bioinformatics
Artificial Intelligence

Background:

Mitochondrial morphology and function are closely related.
Live-cell imaging offers potential for predicting mitochondrial function based on morphology.
Developing computational tools is crucial for analyzing complex mitochondrial data.

Purpose of the Study:

Introduce MoDL, a deep learning algorithm for mitochondrial image segmentation and function prediction.
To demonstrate MoDL's capability in accurately predicting mitochondrial functions from morphological features.
To highlight the potential impact of MoDL on mitochondrial research and drug discovery.

Main Methods:

Developed MoDL, a deep learning algorithm for segmenting and predicting mitochondrial function.

More Related Videos

Author Spotlight: Decoding Mitochondrial Aging

Author Spotlight: Decoding Mitochondrial Aging

Published on: June 30, 2023

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jun 2, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Author Spotlight: Decoding Mitochondrial Aging

Author Spotlight: Decoding Mitochondrial Aging

Published on: June 30, 2023

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Trained MoDL on 20,000 manually labeled super-resolution (SR) images for segmentation.

Employed ensemble learning on over 100,000 SR images with functional assay data for prediction.

Main Results:

MoDL achieved superior accuracy in mitochondrial image segmentation.
The algorithm precisely predicted functions of heterogeneous mitochondria from unseen cell types.
Demonstrated effective prediction with small sample size training through data fine-tuning and retraining.

Conclusions:

MoDL effectively links mitochondrial morphology to function using deep learning.
The algorithm shows significant potential for advancing mitochondrial research and drug discovery.
MoDL provides a powerful tool for exploring mitochondrial form-function relationships across diverse biological contexts.