Search research articles

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

Strain diversity drives heterogeneous responses to tuberculosis combination therapy.

Antimicrobial agents and chemotherapy·2026

Same author

VASCilia is an open-source, deep learning-based tool for 3D analysis of cochlear hair cell stereocilia bundles.

PLoS biology·2026

Same author

Strain diversity drives heterogeneous responses to tuberculosis combination therapy.

bioRxiv : the preprint server for biology·2025

Same author

The <i>TECTB-C225Y</i> Variant Causing Autosomal Dominant Deafness in a Nicaraguan Family Enhances Sensitivity to Noise-Induced Hearing Loss in Mice.

medRxiv : the preprint server for health sciences·2025

Same author

Identification of druggable binding sites and small molecules as modulators of TMC1.

Communications biology·2025

Same author

<i>Frem2</i> Knockout Mice Exhibit Fraser Syndrome Phenotypes and Neonatal Lethality Due to Bilateral Renal Agenesis.

bioRxiv : the preprint server for biology·2024

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: Apr 2, 2026

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

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

Published on: August 13, 2014

SKOOTS: Skeleton-Oriented Object Segmentation for Mitochondria in High-Resolution Cochlear EM Datasets.

Christopher J Buswinka^1,2,3, Richard T Osgood^1,2, Hidetomi Nitta¹

¹Eaton Peabody Laboratories, Mass Eye and Ear, Boston, MA, USA.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)

|March 31, 2026

Summary

This summary is machine-generated.

Manual segmentation of mitochondria is time-consuming. Skeleton-Oriented Object Segmentation (SKOOTS) is a new deep learning framework that efficiently segments large 3D objects like mitochondria in microscopy images, enabling rapid analysis.

Keywords:

aminoglycoside hair cell instance segmentation machine learning mitochondria

More Related Videos

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Analysis of Brain Mitochondria Using Serial Block-Face Scanning Electron Microscopy

Analysis of Brain Mitochondria Using Serial Block-Face Scanning Electron Microscopy

Published on: July 9, 2016

Related Experiment Videos

Last Updated: Apr 2, 2026

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

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

Published on: August 13, 2014

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Analysis of Brain Mitochondria Using Serial Block-Face Scanning Electron Microscopy

Analysis of Brain Mitochondria Using Serial Block-Face Scanning Electron Microscopy

Published on: July 9, 2016

Area of Science:

Biomedical imaging
Computational biology
Cell biology

Background:

Manual segmentation of mitochondria in 3D microscopy datasets is a bottleneck for quantitative analysis.
Existing deep learning segmentation tools are optimized for either high-resolution 3D or low-resolution 2D imaging, failing to address large 3D objects with ambiguous boundaries.
Mitochondria in whole-cell 3D electron microscopy datasets represent a significant challenge due to their complex morphology and unclear boundaries.

Purpose of the Study:

To develop a novel, general-purpose 3D segmentation framework for efficient and accurate segmentation of densely packed, morphologically complex objects.
To address the limitations of current segmentation tools in handling large 3D objects with ambiguous boundaries, specifically mitochondria in 3D electron microscopy datasets.
To enable large-scale, biologically meaningful analysis of 3D biomedical imaging data.

Main Methods:

Developed Skeleton-Oriented Object Segmentation (SKOOTS), a novel 3D segmentation framework.
Combined skeleton-based instance segmentation with a scalable embedding approach.
Applied SKOOTS to segment mitochondria in 3D light and electron microscopy datasets.

Main Results:

SKOOTS demonstrated fast, accurate, and memory-efficient segmentation of large 3D objects.
Successfully segmented over 15,000 mitochondria from cochlear hair cells and supporting cells in under 2 hours on a consumer-grade PC.
Enabled downstream morphological analysis revealing subtle structural changes in mitochondria after aminoglycoside exposure.

Conclusions:

SKOOTS is a versatile and efficient framework for segmenting complex 3D structures in diverse microscopy datasets.
The framework bridges a gap in existing segmentation strategies, facilitating large-scale biological analysis.
SKOOTS is open-source, easy to retrain, and broadly accessible to the research community for various applications.