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

Impact of closed-system suctioning on self-reported dyspnea in mechanically ventilated patients: a prospective observational study.

Frontiers in medicine·2026
Same author

Dual-decoder multi-task network with graph attention mechanism for OCT retinal layer and fluid segmentation.

BMC ophthalmology·2026
Same author

N-Acetylcysteine protects the developing brain in neonatal sepsis-like inflammation via a redox-neurovascular pathway.

Journal of neuroinflammation·2026
Same author

LY6D promotes hepatic steatosis via the GRB2-AMPK-SREBP1 signaling axis.

International journal of obesity (2005)·2026
Same author

Summary of the best evidence for adult nasal high-flow oxygen therapy nebulization management.

Frontiers in medicine·2026
Same author

Twisted Intramolecular Charge Shuttle (TICS) Enables Ultrafast Ratiometric Sensing and Imaging of Nitrite.

Angewandte Chemie (International ed. in English)·2026

Related Experiment Video

Updated: Nov 3, 2025

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

3.1K

RetFluidNet: Retinal Fluid Segmentation for SD-OCT Images Using Convolutional Neural Network.

Loza Bekalo Sappa1, Idowu Paul Okuwobi1, Mingchao Li1

  • 1School of Computer Science and Engineering, Nanjing University of Science and Technology, 200 Xiaolingwei, Nanjing, 210094, China.

Journal of Digital Imaging
|June 3, 2021
PubMed
Summary

A new AI model, RetFluidNet, accurately detects fluid abnormalities in age-related macular degeneration (AMD) using OCT scans. This automated tool aids in early AMD detection and patient monitoring.

Keywords:
Age-related macular degeneration (AMD)Intra-retinal fluid (IRF)Pigment epithelial detachment (PED)Retinal edemaSpectral-domain optical coherence tomography (SD-OCT)Subretinal fluid (SRF)

More Related Videos

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

8.4K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.9K

Related Experiment Videos

Last Updated: Nov 3, 2025

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

3.1K
Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

8.4K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.9K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Age-related macular degeneration (AMD) is a primary cause of irreversible blindness.
  • Fluid accumulation (IRF, SRF, PED) characterizes AMD, but current OCT analysis lacks automated detection.
  • Spectral-domain optical coherence tomography (SD-OCT) is crucial for AMD diagnosis.

Purpose of the Study:

  • To develop an advanced AI model for segmenting and quantifying three key fluid abnormalities in SD-OCT images.
  • To improve the diagnostic capabilities for age-related macular degeneration (AMD).
  • To investigate optimal hyperparameters and network architectures for fluid segmentation.

Main Methods:

  • An improved convolutional neural network (CNN) architecture, RetFluidNet, was designed.
  • The model incorporates skip-connect operations and atrous spatial pyramid pooling (ASPP) for multi-scale feature integration.
  • RetFluidNet was trained and validated on SD-OCT images from 124 AMD patients.

Main Results:

  • RetFluidNet achieved high segmentation accuracy: 80.05% for intra-retinal fluid (IRF), 92.74% for pigment epithelial detachment (PED), and 95.53% for subretinal fluid (SRF).
  • The model demonstrated significant performance improvement over existing methods.
  • The developed architecture offers a balance of accuracy and computational efficiency.

Conclusions:

  • RetFluidNet provides a fully automated and accurate method for detecting fluid abnormalities in AMD.
  • This AI tool can significantly support the early detection and ongoing management of patients with AMD.
  • The findings offer a valuable starting point for future research in AMD fluid segmentation.