Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Repeatability of corneal diameter measured by Sirius versus IOLMaster 700 in myopic eyes: combined with consistency and relationship of sulcus-to-sulcus.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026

Same author

Design and Implementation of an Electromagnetic-Capacitive Coupling Mechanism-Based Material Young's Modulus Measurement System.

Materials (Basel, Switzerland)·2026

Same author

WRCANet: wavelet residual cross-attention network for meibomian gland segmentation.

Biomedical optics express·2026

Same author

OphFusionNet: Uncertainty-driven multi-scale multimodal feature fusion network for ophthalmic diseases classification.

IEEE transactions on medical imaging·2026

Same author

A multifunctional organic additive with diversified elements (F, S, P, and N) for high-performance PEO/LiTFSI electrolytes.

Materials horizons·2026

Same author

Multi-source Unsupervised Domain Adaptation Fundus Lesion Segmentation of Various OCT Devices with Moment Consistency.

IEEE journal of biomedical and health informatics·2026

Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026

Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026

Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026

Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026

Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026

Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 17, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Refining feature representation for accurate fundus lesion segmentation.

Hao Sun¹, Enting Gao², Yongcheng Li³

¹School of Future Science and Engineering, Soochow University, Suzhou, China.

Medical Physics

|April 16, 2026

Summary

This summary is machine-generated.

A new deep learning model, RFENet, improves automated segmentation of retinal lesions like choroidal neovascularization (CNV) and choroidal non-perfusion (CNP) for age-related macular degeneration (AMD) detection. RFENet shows significant performance gains, enhancing diagnostic accuracy.

Keywords:

fundus fluorescein angiography optical coherence tomography retinal lesion segmentation

More Related Videos

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Apr 17, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Accurate segmentation of retinal lesions is crucial for early detection of age-related macular degeneration (AMD).
Choroidal neovascularization (CNV) and choroidal non-perfusion (CNP) are key indicators of AMD, but their variable presentation challenges automated segmentation.
Existing methods struggle with the diverse shapes and appearances of retinal lesions.

Purpose of the Study:

To develop a deep learning model, the Retinal Feature Enhancement Network (RFENet), for improved accuracy and robustness in retinal lesion segmentation.
To address the challenges posed by variable lesion morphology in challenging imaging conditions.
To enhance the early detection of AMD through precise segmentation of CNV and CNP.

Main Methods:

RFENet utilizes the UNeXt backbone with novel Adaptive Feature Refinement Unit (AFRU) and Optimized Channel-Wise Convolution Unit (OCCU) modules.
The model was trained and validated on two expert-annotated datasets: 1070 OCT B-scans (CNV) and 184 FFA images (CNP).
Performance was benchmarked against state-of-the-art models using Dice coefficient and Intersection over Union (IoU) metrics, with statistical significance assessed via t-tests.

Main Results:

RFENet achieved a Dice score of 82.50% and IoU of 71.66% on the CNV dataset, outperforming competing models.
On the CNP dataset, RFENet obtained a Dice score of 74.43% and IoU of 60.80%, slightly exceeding the best benchmark.
Statistical analyses confirmed significant improvements, particularly on the CNV dataset, highlighting RFENet's robustness.

Conclusions:

RFENet demonstrates consistent and statistically significant improvements over existing benchmarks for CNV and CNP lesion segmentation.
The model offers a reliable advancement for automated segmentation of AMD-related lesions.
Source code is publicly available to encourage further research and reproducibility.