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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Inhibitory columnar feedback neurons are involved in motion processing in <i>Drosophila</i>.

eLife·2026
Same author

Tailored dual release of retinol and salicylic acid from salicylate-based poly(anhydride-ester) microspheres with tunable degradation profiles.

International journal of pharmaceutics·2026
Same author

Lateral septal PACAP signaling regulates stress and anxiety reactions.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

Sulfonamide derivatives as tubulin polymerization inhibitors: advances in structural mechanisms, structure-activity relationships, and therapeutic potential in cancer treatment.

RSC advances·2026
Same author

Hyperactivity and Differential Gene Expression in <i>lbx1a<sup>(</sup><sup>-/</sup><sup>-)</sup></i> Zebrafish Larvae.

Cells·2025
Same author

hiPSC-derived cortical neurons from ADHD individuals reveal dysregulated glutamatergic development.

Molecular psychiatry·2025
Same journal

SqueakPose Studio, an end-to-end platform for pose estimation and real-time edge-AI deployment.

eLife·2026
Same journal

Mechanistic insights into transcriptional regulation of ARHGAP36 expression identify a factor predictive of neuroblastoma survival.

eLife·2026
Same journal

Activity-dependent CO<sub>2</sub> production in the axon triggers opening of Connexin32 in the Schwann cell paranode.

eLife·2026
Same journal

Lipid packing contributes to the confinement of caveolae to the plasma membrane.

eLife·2026
Same journal

A coma pattern-based autofocusing method resolves bacterial cold shock response at single-cell level.

eLife·2026
Same journal

Non-canonical amino acid incorporation enables minimally disruptive labeling of stress granule and TDP-43 proteinopathy.

eLife·2026
See all related articles

Related Experiment Video

Updated: Dec 5, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

On the objectivity, reliability, and validity of deep learning enabled bioimage analyses.

Dennis Segebarth1, Matthias Griebel2, Nikolai Stein2

  • 1Institute of Clinical Neurobiology, University Hospital Würzburg, Würzburg, Germany.

Elife
|October 19, 2020
PubMed
Summary
This summary is machine-generated.

Automating bioimage analysis with deep learning (DL) requires objective annotations. This study shows that using multiple annotators for ground truth estimation and training model ensembles improves reliability and validity in fluorescent image analysis.

Keywords:
bioimage informaticscomputational biologydeep learningfluorescence microscopymouseneuroscienceobjectivityreproducibilitysystems biologyvalidityzebrafish

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.3K

Related Experiment Videos

Last Updated: Dec 5, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.3K

Area of Science:

  • Life Sciences
  • Bioimage Analysis
  • Deep Learning Applications

Background:

  • Bioimage analysis of fluorescent labels is crucial in life sciences.
  • Deep learning (DL) automates manual image analysis but relies on annotated data.
  • Subjectivity in annotating low signal-to-noise fluorescent features can lead to biased DL models.

Purpose of the Study:

  • To evaluate an integrated pipeline for DL-based bioimage analysis.
  • To mitigate risks associated with subjective manual annotations.
  • To establish objectivity, reliability, and validity in DL model training for bioimage analysis.

Main Methods:

  • Comparison of different DL-based analysis approaches.
  • Utilized data from two model organisms (mice, zebrafish) across five laboratories.
  • Implemented ground truth estimation using multiple human annotators and trained model ensembles.

Main Results:

  • Ground truth estimation from multiple annotators enhanced objectivity in fluorescent feature annotations.
  • Ensembles of DL models trained on estimated ground truth demonstrated reliability and validity.
  • The integrated pipeline effectively addressed challenges in DL-based bioimage analysis.

Conclusions:

  • Multiple human annotators are key to establishing objective ground truth for bioimage analysis.
  • Model ensembles trained on consensus ground truth ensure reproducible and valid DL-based analyses.
  • Provides guidelines for robust and reproducible deep learning applications in bioimage analysis.