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

The microstructure-weighted human connectome: network properties and structure-function correlations across spatial scales.

bioRxiv : the preprint server for biology·2026

Same author

ProteomeLM: A proteome-scale language model enables accurate and rapid prediction of protein-protein interactions and gene essentiality across taxa.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Automated Optimization of Bacterial Tracking Pipelines With TrackMate 8.

Current protocols·2026

Same author

Love-thy-neighbor: neural networks for tracking and lineage tracing in budding yeast.

Bioinformatics advances·2026

Same author

Environment heterogeneity creates fast amplifiers of natural selection in graph-structured populations.

Nature communications·2026

Same author

Out-of-Equilibrium Selection Pressure Enhances Inference from Protein Sequence Data.

Physical review letters·2026

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: Nov 30, 2025

Reconstruction of Single-Cell Innate Fluorescence Signatures by Confocal Microscopy

Reconstruction of Single-Cell Innate Fluorescence Signatures by Confocal Microscopy

Published on: May 27, 2020

A convolutional neural network segments yeast microscopy images with high accuracy.

Nicola Dietler^1,2, Matthias Minder¹, Vojislav Gligorovski¹

¹Laboratory of the Physics of Biological Systems, Institute of Physics, École polytechnique fédérale de Lausanne (EPFL), Lausanne, Switzerland.

Nature Communications

|November 13, 2020

Summary

We developed YeaZ, a convolutional neural network (CNN) for accurate yeast cell segmentation in microscopy images, overcoming challenges with budding and crowded cells. This tool enables efficient large-scale image analysis to uncover new biological insights.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

4D Microscopy of Yeast

4D Microscopy of Yeast

Published on: April 28, 2019

Related Experiment Videos

Last Updated: Nov 30, 2025

Reconstruction of Single-Cell Innate Fluorescence Signatures by Confocal Microscopy

Reconstruction of Single-Cell Innate Fluorescence Signatures by Confocal Microscopy

Published on: May 27, 2020

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

4D Microscopy of Yeast

4D Microscopy of Yeast

Published on: April 28, 2019

Area of Science:

Cell biology
Computational biology
Microscopy image analysis

Background:

Accurate cell segmentation is crucial for high-throughput microscopy but challenging for Saccharomyces cerevisiae due to budding and cell crowding.
Existing segmentation methods struggle with irregular cell shapes and dense populations, limiting large-scale biological discovery.

Purpose of the Study:

To develop an accurate and efficient automated method for segmenting yeast cells in microscopy images.
To create a user-friendly tool for researchers to analyze large datasets and explore yeast cell morphology and behavior.

Main Methods:

Development of YeaZ, a convolutional neural network (CNN) trained on over 10,000 high-quality segmented yeast images.
Implementation of a cell-cell boundary test to eliminate the need for fluorescent markers.
Creation of a graphical user interface and web application for system accessibility and expansion.

Main Results:

YeaZ demonstrates high accuracy in segmenting yeast cells, including buds and irregularly shaped cells.
The CNN outperforms existing segmentation methods on benchmark datasets and shows good transferability to various conditions.
Analysis of ≈2200 cells revealed that yeast morphogenesis control initiates early and progresses gradually.

Conclusions:

YeaZ provides a robust and efficient solution for yeast cell segmentation, addressing limitations of current methods.
The developed tool facilitates large-scale image processing, enabling deeper biological insights into cell morphology and development.
The findings suggest a more gradual and earlier onset of morphogenesis control in yeast than previously understood.