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

Downsampling01:20

Downsampling

872
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
872

You might also read

Related Articles

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

Sort by
Same author

Simultaneous OCT A-scan depth ranging and C-scan volume imaging for intraoperative robotic retinal surgery guidance.

Biomedical optics express·2025
Same author

Wearable optical coherence tomography angiography probe for freely moving mice.

Biomedical optics express·2024
Same author

Automated robot-assisted wide-field optical coherence tomography using structured light camera.

Biomedical optics express·2023
Same author

Protocol for profiling cell-centric assembled single-cell human transcriptome data in hECA.

STAR protocols·2022
Same author

Visible Light-Promoted Radical-Mediated Ring-Opening/Cyclization of Vinyl Benzotriazoles: An Alternative Approach to Phenanthridines.

Organic letters·2022
Same author

How to Achieve Sufficient Endogenous Insulin Suppression in Euglycemic Clamps Assessing the Pharmacokinetics and Pharmacodynamics of Long-Acting Insulin Preparations Employing Healthy Volunteers.

Frontiers in pharmacology·2022

Related Experiment Video

Updated: May 4, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.3K

Time-step encoded high-frequency enhanced diffusion model for OCT retinal image denoising.

Boyu Yang1,2,3, Yong Huang1,2,3,4, Yingxiong Xie1,2

  • 1Beijing Institute of Technology, School of Optics and Photonics, Beijing, 100081, China.

Biomedical Optics Express
|November 26, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces THFN-OCT, a novel deep learning model for optical coherence tomography (OCT) denoising. It enhances high-frequency details in retinal images, improving diagnostic accuracy by overcoming limitations of current methods.

More Related Videos

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

1.0K
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.3K

Related Experiment Videos

Last Updated: May 4, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.3K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

1.0K
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.3K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Optical coherence tomography (OCT) provides high-resolution retinal imaging but suffers from speckle noise, degrading image quality.
  • Current deep learning denoising methods often oversmooth OCT images, losing crucial high-frequency details necessary for accurate retinal structure analysis.

Purpose of the Study:

  • To develop an advanced deep learning model for OCT image denoising that preserves high-frequency details.
  • To improve the accuracy of retinal structure recovery in OCT images affected by speckle noise.

Main Methods:

  • Proposed a time-enhanced high-frequency network (THFN-OCT) based on the cold diffusion framework.
  • Decoupled frequency-domain information, processing components separately with cross-domain connections.
  • Introduced a timestep-aware attention module to guide reconstruction based on diffusion timestep impacts.

Main Results:

  • The THFN-OCT model demonstrated superior performance in denoising OCT images compared to existing algorithms.
  • Preservation of high-frequency details was achieved while maintaining effective noise reduction.
  • Experiments on public and private datasets validated the method's efficacy.

Conclusions:

  • The proposed THFN-OCT model effectively addresses the limitations of current OCT denoising techniques.
  • This method offers improved recovery of true retinal structures, enhancing the diagnostic value of OCT imaging.
  • The approach shows significant potential for clinical application in ophthalmology.