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 Video

Updated: Jan 11, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Multi-scale target-aware representation learning for fundus image enhancement.

Haofan Wu1, Yin Huang2, Yuqing Wu3

  • 1Research Center for Translational Medicine, Medical Innovation Center and State Key Laboratory of Cardiology, Shanghai East Hospital, Shanghai, 200120, China; The Institute for Biomedical Engineering & Nano Science, Tongji University School of Medicine, Shanghai, 200120, China; Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China.

Neural Networks : the Official Journal of the International Neural Network Society
|November 12, 2025
PubMed
Summary

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

Telomerase as a therapeutic Bullseye: advances in cancer treatment and clinical trials : A comprehensive review of small molecule inhibitors, antisense oligonucleotides, and immunotherapeutic strategies targeting the telomerase catalytic subunit (hTERT).

Biological research·2026
Same author

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Nitric Oxide-Mediated Minimally Invasive Neuromodulation through Gut-Brain Axis via a Bioelectronic Microdevice for Relieving Depressive Symptoms.

ACS nano·2026
Same author

Gut dysbiosis associated with neonatal respiratory distress syndrome and biological plausibility of disease-specific probiotic intervention: a translational study.

Journal of translational medicine·2026
Same author

Loss-of-Function Variants in CCDC189 Cause Human Oligoasthenoteratozoospermia by Disrupting Sperm Flagellar and Acrosomal Architecture.

Andrology·2026
Same author

Insights into the antibacterial, antifungal, and antiparasitic activities of functionalized ZnO quantum dots.

Scientific reports·2026
This summary is machine-generated.

This study introduces a novel multi-scale target-aware representation learning framework (MTRL-FIE) for enhancing low-quality fundus images. The method effectively restores details and highlights pathological regions, improving ophthalmic diagnostics.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • High-quality fundus images are crucial for diagnosing eye diseases.
  • Existing enhancement methods often fail to capture multi-scale information or focus on specific targets like lesions.
  • Low resolution and signal-to-noise ratio degrade fundus image quality.

Purpose of the Study:

  • To develop a unified framework for comprehensive fundus image enhancement.
  • To improve the recovery of multi-scale information and pathological details.
  • To create a target-aware enhancement method for better clinical diagnosis.

Main Methods:

  • Proposed a multi-scale target-aware representation learning framework (MTRL-FIE).
  • Utilized a multi-scale feature encoder (MFE) with wavelet decomposition for multi-scale information embedding.
Keywords:
Attention mechanismFundus imageImage enhancementWavelet transform

More Related Videos

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

3.3K

Related Experiment Videos

Last Updated: Jan 11, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
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

3.3K
  • Designed a structure-preserving hierarchical decoder (SHD) with group attention for feature fusion and artifact reduction.
  • Incorporated a target-aware feature aggregation (TFA) module to enhance pathological regions.

    • Main Results:

    • MTRL-FIE demonstrated superior fundus image enhancement performance on multiple datasets.
    • Achieved better results compared to state-of-the-art methods with a more lightweight architecture.
    • Showcased effectiveness in enhancing lesions and preserving structural details.

    Conclusions:

    • MTRL-FIE provides an effective and generalizable solution for fundus image enhancement.
    • The framework's target-aware approach is crucial for medical image-based diagnosis.
    • The method shows potential for broader clinical applications in ophthalmic imaging.