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

Aliasing01:18

Aliasing

311
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
311

You might also read

Related Articles

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

Sort by
Same author

Nursing strategies for severe poststroke fatigue: a case report of a structured, multidimensional intervention program.

Frontiers in rehabilitation sciences·2026
Same author

Notch Signaling Reprograms Glial Lipid Metabolism to Promote Hypoxia Resistance.

bioRxiv : the preprint server for biology·2026
Same author

Epidemiological profile of respiratory viruses associated with influenza-like illness and severe acute respiratory infection in Guangzhou, China, 2024-2025.

Frontiers in public health·2026
Same author

Protein-Protein Interactions in Food Systems: Analytical Advances and Quality Implications.

Foods (Basel, Switzerland)·2026
Same author

Protein-Carbohydrate Interactions in Food Matrices and Their Effects on Food Quality.

Foods (Basel, Switzerland)·2026
Same author

Analysis of Epidemiological and Molecular Characteristics of Bocavirus in Guangzhou.

Viruses·2026

Related Experiment Video

Updated: Nov 1, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.4K

Accurate and practical feature extraction from noisy holograms.

Siddharth Rawat, Anna Wang

    Applied Optics
    |June 18, 2021
    PubMed
    Summary

    This study introduces a deep learning method using generative adversarial networks to accurately extract quantitative phase imaging data from noisy holograms. This overcomes limitations of traditional methods, enabling better cell analysis in challenging conditions.

    Area of Science:

    • Biophysics
    • Optical Imaging
    • Machine Learning

    Background:

    • Quantitative phase imaging (QPI) via holographic microscopy offers non-invasive cell analysis.
    • Low signal-to-noise ratios in biological holograms hinder accurate feature extraction.
    • Traditional phase-unwrapping methods are computationally intensive and often fail with noisy data.

    Purpose of the Study:

    • To develop a novel deep learning strategy for robust phase map generation from noisy holograms.
    • To overcome the limitations of conventional phase-unwrapping techniques in QPI.
    • To enable accurate quantitative feature extraction from low-quality holographic data.

    Main Methods:

    • Conditional generative adversarial networks (Pix2Pix architecture) were employed for phase generation.

    More Related Videos

    Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization
    10:28

    Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

    Published on: July 5, 2016

    10.5K
    Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display
    09:04

    Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

    Published on: January 14, 2020

    10.0K

    Related Experiment Videos

    Last Updated: Nov 1, 2025

    Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
    10:16

    Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

    Published on: February 8, 2014

    12.4K
    Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization
    10:28

    Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

    Published on: July 5, 2016

    10.5K
    Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display
    09:04

    Recording Ultra-Realistic Full-Color Analog Holograms for Use in a Moving Hologram Display

    Published on: January 14, 2020

    10.0K
  • The network was trained on random surfaces and subsequently tested on various objects.
  • Performance was evaluated using simulated and real biological samples (HL-60 cells).

    • Main Results:

    • The generative adversarial network successfully generated accurate phase maps from noisy holograms.
    • The method demonstrated reliable phase map generation even with rapid training on related objects.
    • Accurate morphological and quantitative features were extracted from HL-60 cell phase maps where traditional methods failed.

    Conclusions:

    • Deep learning-based phase generation effectively decouples noise from signal in holographic microscopy.
    • This approach significantly enhances the applicability of QPI to real-world, noisy biological systems.
    • The Pix2Pix-based strategy offers a computationally efficient and accurate alternative for phase map reconstruction.