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

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

Long-range mutual activation establishes Rho and Rac polarity during cell migration.

Nature cell biology·2026

Same author

Use of virtual reality medical hypnosis for anxiolytic purposes during frozen embryo transfer: A prospective pilot study.

PloS one·2026

Same author

Live birth after oocyte donation in women with Turner syndrome compared with other causes of premature ovarian insufficiency: a retrospective cohort study.

Journal of assisted reproduction and genetics·2026

Same author

Spatiotemporal mapping of the contractile and adhesive forces sculpting early C. elegans embryos.

Developmental cell·2026

Same author

Restoring the tumour mechanophenotype of vocal fold cancer reverts its malignant properties.

Nature materials·2026

Same author

Hearing Loss in Parkinson's Disease: A Systematic Review and Meta-Analysis.

Movement disorders : official journal of the Movement Disorder Society·2026

Same journal

MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes.

ArXiv·2026

Same journal

A Positron Range Correction with Texture Preservation Framework in PET Imaging.

ArXiv·2026

Same journal

Automated optimization of force field parameters against ensemble-averaged measurements with Bayesian Inference of Conformational Populations.

ArXiv·2026

Same journal

Droplet Fusion as a Relaxation Process: Comparison with Shape Recovery of Newtonian and Viscoelastic Droplets.

ArXiv·2026

Same journal

Ridge-filter crosstalk in conformal proton FLASH planning: dependence on beamlet pitch and iterative mitigation.

ArXiv·2026

Same journal

Electrochemical DNA Hairpin Sensors for Differentiating Small Molecule Intercalation from Minor Groove Binding.

ArXiv·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 22, 2025

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

Self-Supervised Z-Slice Augmentation for 3D Bio-Imaging via Knowledge Distillation.

Alessandro Pasqui¹, Sajjad Mahdavi¹, Benoit Vianay²

¹Center for Interdisciplinary Research in Biology (CIRB), Collège de France, Université PSL, CNRS, INSERM, 75005 Paris, France.

|March 17, 2025

Summary

This summary is machine-generated.

ZAugNet enhances z-resolution in 3D biological images using self-supervised deep learning. This method improves accuracy for cellular measurements in microscopy, offering a scalable solution for large-scale 3D imaging.

Keywords:

3D image enhancement generative adversarial network knowledge distillation

More Related Videos

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Published on: February 28, 2021

Related Experiment Videos

Last Updated: May 22, 2025

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

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Published on: February 28, 2021

Area of Science:

Biophysics
Computational Biology
Microscopy

Background:

Three-dimensional (3D) biological microscopy is crucial for understanding complex cellular structures.
Poor z-resolution in 3D microscopy limits accurate cellular measurements.
Existing techniques struggle with phototoxicity and sample properties affecting image quality.

Purpose of the Study:

To introduce ZAugNet, a novel deep learning method for enhancing z-resolution in 3D biological images.
To provide a fast, accurate, and self-supervised solution for improving z-axis image quality.
To develop scalable augmentation solutions for large-scale 3D imaging datasets.

Main Methods:

Developed ZAugNet, a self-supervised deep learning model utilizing a generative adversarial network (GAN) architecture.
Employed nonlinear interpolation between consecutive slices to enhance z-resolution.
Incorporated knowledge distillation to optimize prediction speed without sacrificing accuracy.
Created ZAugNet+, an extended version for continuous interpolation and handling nonuniform slice spacing.

Main Results:

ZAugNet effectively doubles z-resolution through iterative nonlinear interpolation.
The method demonstrated superior performance compared to competing techniques across various microscopy modalities and biological samples.
ZAugNet achieves high prediction speed and accuracy.
ZAugNet+ offers flexibility for datasets with irregular slice spacing.

Conclusions:

ZAugNet and ZAugNet+ provide effective, scalable solutions for improving z-resolution in 3D biological imaging.
These deep learning tools enhance the accuracy of cellular measurements derived from microscopy data.
The open-source availability in PyTorch with a Colab interface promotes accessibility for the scientific community.