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

Improved ecological risk assessment of phenol in sediments via species sensitivity distribution and equilibrium partitioning method using water toxicity data.

Scientific reports·2026
Same author

AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms.

Biomedical optics express·2026
Same author

Toward animal-free cardiac safety testing: Early detection of cardiotoxic reactions via multimodal in vitro readouts.

Journal of advanced research·2026
Same author

Synthesis and characterization of dialdehyde starch-crosslinked ε-poly-L-lysine for enhanced harvesting of Chlorella vulgaris: Flocculation performance, kinetics, and process integration.

Bioresource technology·2025
Same author

Automated phenotypic analysis and classification of drug-treated cardiomyocytes via synergized time-lapse holographic imaging and deep learning.

Computer methods and programs in biomedicine·2025
Same author

Automated fast label-free quantification of cardiomyocyte dynamics with raw holograms for cardiotoxicity screening.

Biomedical optics express·2025

Related Experiment Video

Updated: Nov 14, 2025

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.8K

High-throughput label-free cell detection and counting from diffraction patterns with deep fully convolutional neural

Faliu Yi1, Seonghwan Park2, Inkyu Moon2

  • 1University of Texas Southwestern Medical Center, Department of Clinical Science, Dallas, Texas, United States.

Journal of Biomedical Optics
|March 9, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces deep fully convolutional networks (FCNs) for high-throughput, label-free detection and counting of red blood cells (RBCs) using digital holographic microscopy (DHM) diffraction patterns. The method achieves 99% accuracy, offering a faster alternative to traditional cell analysis.

Keywords:
cell countingdeep learningdigital holographic microscopyholography applicationoptical information processingred blood cell analysis

More Related Videos

A Label-free Technique for the Spatio-temporal Imaging of Single Cell Secretions
09:09

A Label-free Technique for the Spatio-temporal Imaging of Single Cell Secretions

Published on: November 23, 2015

8.8K
Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation
08:34

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation

Published on: August 8, 2025

1.5K

Related Experiment Videos

Last Updated: Nov 14, 2025

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.8K
A Label-free Technique for the Spatio-temporal Imaging of Single Cell Secretions
09:09

A Label-free Technique for the Spatio-temporal Imaging of Single Cell Secretions

Published on: November 23, 2015

8.8K
Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation
08:34

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation

Published on: August 8, 2025

1.5K

Area of Science:

  • Biomedical Imaging
  • Computational Biology
  • Microscopy

Background:

  • Digital holographic microscopy (DHM) is valuable for studying semitransparent biological specimens like red blood cells (RBCs).
  • Accurate single-cell detection and counting are crucial for biomarker discovery and disease diagnostics.
  • Current phase-based analysis of DHM images is inefficient due to complex reconstruction algorithms.

Purpose of the Study:

  • To develop a novel, efficient method for high-throughput, label-free detection and counting of biological cells.
  • To utilize raw hologram images directly, bypassing complex phase reconstruction.
  • To explore the application of deep fully convolutional networks (FCNs) for cell analysis.

Main Methods:

  • Recorded raw diffraction patterns of RBCs using DHM.
  • Generated ground-truth masks from phase images reconstructed from holograms.
  • Trained a deep FCN (UNet) on diffraction pattern images for label-free cell detection and counting.

Main Results:

  • Achieved high-throughput, label-free RBC counting with 99% accuracy.
  • Demonstrated a throughput rate exceeding 288 cells per second within a 200x200 μm field of view.
  • FCNs outperformed traditional convolutional neural networks in accuracy and throughput.

Conclusions:

  • Deep FCNs successfully enable high-throughput, label-free cell detection and counting from raw hologram diffraction patterns.
  • This approach offers a promising direct analysis method for biological specimens using DHM.
  • The developed technique significantly enhances efficiency and accuracy in cell analysis.