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

[C-ring cleavage of liquiritigenin extracted from licorice roots by an oxygen-tolerant bovine rumen bacterium strain Aeroto-Niu-O16].

Yao xue xue bao = Acta pharmaceutica Sinica·2012
Same author

Correlation between base-excision repair gene polymorphisms and levels of in-vitro BPDE-induced DNA adducts in cultured peripheral blood lymphocytes.

PloS one·2012
Same author

Design of compensation coils for EMI suppression in magnetostrictive linear position sensors.

Sensors (Basel, Switzerland)·2012
Same author

Polarization of a diffuse soft particle subjected to an alternating current field.

Langmuir : the ACS journal of surfaces and colloids·2012
Same author

A single nucleotide mutation in NS2A of Japanese encephalitis-live vaccine virus (SA14-14-2) ablates NS1' formation and contributes to attenuation.

The Journal of general virology·2012
Same author

[Acupuncture combined with pricking blood, cupping and moxibustion for 199 cases of intractable facial palsy].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2012

Related Experiment Video

Updated: Aug 9, 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

2.9K

Self-training adversarial learning for cross-domain retinal OCT fluid segmentation.

Xiaohui Li1, Sijie Niu1, Xizhan Gao1

  • 1Shandong Provincial Key Laboratory of Network based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, 250022, Shandong, China.

Computers in Biology and Medicine
|February 23, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel self-training adversarial learning framework for unsupervised domain adaptation in optical coherence tomography (OCT) fluid segmentation. The method improves cross-domain segmentation accuracy for macular edema, crucial for assessing disease progression and treatment outcomes.

Keywords:
Adversarial transfer learningMedical image segmentationOptical coherence tomographySelf-trainingUnsupervised domain adaptation

More Related Videos

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

8.6K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

488

Related Experiment Videos

Last Updated: Aug 9, 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

2.9K
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

8.6K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

488

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate macular edema segmentation in optical coherence tomography (OCT) is vital for disease assessment.
  • Deep learning models struggle with OCT fluid segmentation due to low contrast and domain shift between devices.
  • Cross-domain analysis of OCT images is challenging due to performance degradation.

Purpose of the Study:

  • To develop an unsupervised domain adaptation framework for retinal OCT fluid segmentation.
  • To address challenges in cross-domain OCT image analysis and improve segmentation accuracy.
  • To enable robust joint assessment of disease progression and treatment outcomes.

Main Methods:

  • Proposed a self-training adversarial learning framework for unsupervised domain adaptation.
  • Developed image style transfer and fine-grained feature transfer modules to reduce domain discrepancies.
  • Implemented a self-training module using discrepancy and similarity strategies for iterative model training.

Main Results:

  • The proposed method effectively reduces appearance and feature discrepancies between different OCT devices.
  • Achieved comparable results on cross-domain retinal OCT fluid segmentation against state-of-the-art methods.
  • Demonstrated effectiveness on two challenging datasets, enhancing joint analysis capabilities.

Conclusions:

  • The novel framework significantly improves unsupervised domain adaptation for OCT fluid segmentation.
  • The method offers a robust solution for analyzing multi-domain OCT images.
  • This advancement supports more accurate disease progression and treatment outcome assessments in ophthalmology.