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

Polyphasic taxonomic characterization of Brachybacterium netajii sp. nov., a metabolically versatile bacterium isolated from the river Ganges, India.

Scientific reports·2026
Same author

Erratum: Evaluating the<i>in vivo</i>glial response to miniaturized parylene cortical probes coated with an ultra-fast degrading polymer to aid insertion (2018<i>J. Neural Eng</i>.<b>15</b>036002).

Journal of neural engineering·2026
Same author

Corrigendum to "Caffeine inhibits hypoxia-induced nuclear accumulation in HIF-1α and promotes neonatal neuronal survival" [Experimental Neurology, 317 (2019) 66-77].

Experimental neurology·2026
Same author

Microscopic simulation and statistical analysis of gas gain fluctuations in gaseous detectors.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

Biocompatible <i>de novo</i> indolylchalcones as platelet aggregation inhibition and diabetic wound healing agents.

RSC medicinal chemistry·2026
Same author

Structural and computational supported development of 2,5-disubstituted-1,3,4-oxadiazole analogues as active LOX, urease, and α-glucosidase inhibitors.

Scientific reports·2026

Related Experiment Video

Updated: Oct 7, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K

Sub-micro scale cell segmentation using deep learning.

Volkan Müjdat Tiryaki1, Virginia M Ayres2, Ijaz Ahmed3

  • 1Department of Computer Engineering, School of Engineering, Siirt University, Siirt, Turkey.

Cytometry. Part a : the Journal of the International Society for Analytical Cytology
|January 9, 2022
PubMed
Summary
This summary is machine-generated.

Deep learning, specifically U-nets, enhances automated cell segmentation using atomic force microscopy (AFM) images. This method accurately identifies nanoscale cellular features, improving research speed and discovery potential.

Keywords:
astrocyteatomic force microscopycell culturecell morphology

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

3.0K
Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.3K

Related Experiment Videos

Last Updated: Oct 7, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
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

3.0K
Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.3K

Area of Science:

  • Biophysics
  • Cell Biology
  • Machine Learning

Background:

  • Automated cell segmentation is crucial for analyzing cellular responses, especially with advanced imaging techniques revealing nanoscale features.
  • Manual analysis of these small features is time-consuming and limits research speed.
  • Deep learning offers a promising solution for accurate and rapid cell segmentation.

Purpose of the Study:

  • To investigate semantic cell segmentation systems for astrocytes using U-net deep learning models.
  • To evaluate the impact of network hyperparameters and input image modalities (AFM height, deflection, friction) on segmentation performance.
  • To assess the effectiveness of transfer learning methods for improving segmentation accuracy.

Main Methods:

  • Implementation of fully convolutional neural networks (U-nets) for semantic cell segmentation.
  • Experimentation with varying network layers, loss functions, and input image types (AFM height, deflection, friction).
  • Application of transfer learning techniques (VGG16, VGG19, Xception) to enhance segmentation performance.

Main Results:

  • AFM height images provided more discriminative features for cell segmentation compared to deflection and friction images.
  • Transfer learning methods resulted in statistically significant improvements in segmentation performance.
  • The proposed system achieved high precision with an accuracy of 0.9849, Matthews correlation coefficient of 0.9218, and Dice's similarity coefficient of 0.9306 on AFM test images.

Conclusions:

  • The developed U-net based system demonstrates high precision and success in segmenting astrocytes from AFM images.
  • This automated approach accelerates the investigation of nanoscale cellular features, potentially leading to new discoveries.
  • The study highlights the efficacy of deep learning and transfer learning for high-resolution cell segmentation in biophysical research.