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 Experiment Videos

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

Xuan Dong1, Idowu Paul Okuwobi2,3,4

  • 1School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, 541004, China.

BMC Ophthalmology
|July 4, 2026
PubMed
Summary

Related Concept Videos

Parallel Processing01:20

Parallel Processing

The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...

You might also read

Related Articles

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

Sort by
Same author

Metabolic and Transcriptomic Basis of Quality Divergence in Onions (<i>Allium cepa</i> L.) with Different Bulb Colors.

Plants (Basel, Switzerland)·2026
Same author

Retinoid dynamics in immune cells during age-related diseases.

Cytokine & growth factor reviews·2026
Same author

EIF4A3 facilitates METTL3-mediated m<sup>6</sup>A methylation of circPCMTD1 to drive bladder cancer progression via miR-3681-5p/HPSE axis.

Cellular signalling·2026
Same author

PHP (phosphoric acid-hydrogen peroxide) pretreatment for efficiently deconstructing lignocellulose with simultaneously organic pollutants degradation by the derived-gas.

Bioresource technology·2026
Same author

The Mitogenomes and Phylogenetic Relationships of the Tribe Aedini in Culicidae (Diptera).

Ecology and evolution·2026
Same author

Developing a mobile RNA delivery system for grafting trait improvement.

EMBO reports·2026

A new AI method accurately segments retinal layers and fluid in optical coherence tomography (OCT) images for diabetic macular edema (DME). This aids in early diagnosis and monitoring of visual impairment caused by diabetes.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic macular edema (DME) causes significant visual impairment and blindness.
  • Accurate segmentation of retinal layers and fluid in OCT images is crucial for DME diagnosis but challenging due to image artifacts.
  • Current segmentation methods struggle with irregular fluid distribution and low contrast boundaries.

Purpose of the Study:

  • To develop an effective deep learning method for joint segmentation of retinal layers and pathological fluid regions in OCT images.
  • To improve automated analysis and clinical screening for diabetic macular edema.

Main Methods:

  • A novel dual-decoder multi-task network with graph attention was proposed.
  • The network incorporated cross-decoder spatial attention and a global reasoning module for enhanced feature interaction and anatomical dependency capture.
Keywords:
Cross-decoder spatial attentionDiabetic macular edemaOptical coherence tomographyRetinal fluid segmentationRetinal layer segmentation

Related Experiment Videos

  • Experiments were conducted on the Duke DME dataset using subject-independent cross-validation.

    • Main Results:

    • The proposed method demonstrated superior performance compared to mainstream segmentation models.
    • It achieved stable accuracy in normal retinal layer segmentation and competitive performance in fluid region identification.
    • The method effectively reduced interference from pathological changes and improved segmentation boundary consistency.

    Conclusions:

    • The developed method enables accurate joint segmentation of retinal layers and fluid regions in OCT images.
    • This provides a reliable automated analysis tool for diabetic macular edema.
    • The tool can serve as an effective auxiliary reference for clinical screening and quantitative evaluation of DME.