Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images

Abstract Mitochondria are central to cellular energy production and regulation, with their morphology tightly linked to functional performance. Precise analysis of mitochondrial ultrastructure is crucial for understanding cellular bioenergetics and pathology. While transmission electron microscopy (...

Full description

Saved in:
Bibliographic Details
Main Authors: Chan Jang, Hojun Lee, Jaejun Yoo, Haejin Yoon
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03311-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850243415381377024
author Chan Jang
Hojun Lee
Jaejun Yoo
Haejin Yoon
author_facet Chan Jang
Hojun Lee
Jaejun Yoo
Haejin Yoon
author_sort Chan Jang
collection DOAJ
description Abstract Mitochondria are central to cellular energy production and regulation, with their morphology tightly linked to functional performance. Precise analysis of mitochondrial ultrastructure is crucial for understanding cellular bioenergetics and pathology. While transmission electron microscopy (TEM) remains the gold standard for such analyses, traditional manual segmentation methods are time-consuming and prone to error. In this study, we introduce a novel deep learning framework that combines probabilistic interactive segmentation with automated quantification of mitochondrial morphology. Leveraging uncertainty analysis and real-time user feedback, the model achieves comparable segmentation accuracy while reducing analysis time by 90% compared to manual methods. Evaluated on both benchmark Lucchi++ datasets and real-world TEM images of mouse skeletal muscle, the pipeline not only improved efficiency but also identified key pathological differences in mitochondrial morphology between wild-type and mdx mouse models of Duchenne muscular dystrophy. This automated approach offers a powerful, scalable tool for mitochondrial analysis, enabling high-throughput and reproducible insights into cellular function and disease mechanisms.
format Article
id doaj-art-5bcbb4a9488a4e5585ed236543da5e8a
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5bcbb4a9488a4e5585ed236543da5e8a2025-08-20T02:00:00ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-03311-1Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy imagesChan Jang0Hojun Lee1Jaejun Yoo2Haejin Yoon3Graduate School of Artificial Intelligence, Ulsan National Institute of Science & TechnologyDepartment of Biological Sciences, Ulsan National Institute of Science & TechnologyGraduate School of Artificial Intelligence, Ulsan National Institute of Science & TechnologyDepartment of Biological Sciences, Ulsan National Institute of Science & TechnologyAbstract Mitochondria are central to cellular energy production and regulation, with their morphology tightly linked to functional performance. Precise analysis of mitochondrial ultrastructure is crucial for understanding cellular bioenergetics and pathology. While transmission electron microscopy (TEM) remains the gold standard for such analyses, traditional manual segmentation methods are time-consuming and prone to error. In this study, we introduce a novel deep learning framework that combines probabilistic interactive segmentation with automated quantification of mitochondrial morphology. Leveraging uncertainty analysis and real-time user feedback, the model achieves comparable segmentation accuracy while reducing analysis time by 90% compared to manual methods. Evaluated on both benchmark Lucchi++ datasets and real-world TEM images of mouse skeletal muscle, the pipeline not only improved efficiency but also identified key pathological differences in mitochondrial morphology between wild-type and mdx mouse models of Duchenne muscular dystrophy. This automated approach offers a powerful, scalable tool for mitochondrial analysis, enabling high-throughput and reproducible insights into cellular function and disease mechanisms.https://doi.org/10.1038/s41598-025-03311-1Mitochondrial morphologyDeep learning segmentationTransmission electron microscopy imagingInteractive segmentationUncertainty analysisAutomated quantification
spellingShingle Chan Jang
Hojun Lee
Jaejun Yoo
Haejin Yoon
Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
Scientific Reports
Mitochondrial morphology
Deep learning segmentation
Transmission electron microscopy imaging
Interactive segmentation
Uncertainty analysis
Automated quantification
title Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
title_full Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
title_fullStr Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
title_full_unstemmed Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
title_short Deep learning-driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
title_sort deep learning driven automated mitochondrial segmentation for analysis of complex transmission electron microscopy images
topic Mitochondrial morphology
Deep learning segmentation
Transmission electron microscopy imaging
Interactive segmentation
Uncertainty analysis
Automated quantification
url https://doi.org/10.1038/s41598-025-03311-1
work_keys_str_mv AT chanjang deeplearningdrivenautomatedmitochondrialsegmentationforanalysisofcomplextransmissionelectronmicroscopyimages
AT hojunlee deeplearningdrivenautomatedmitochondrialsegmentationforanalysisofcomplextransmissionelectronmicroscopyimages
AT jaejunyoo deeplearningdrivenautomatedmitochondrialsegmentationforanalysisofcomplextransmissionelectronmicroscopyimages
AT haejinyoon deeplearningdrivenautomatedmitochondrialsegmentationforanalysisofcomplextransmissionelectronmicroscopyimages