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

Development of APH003─a Highly Potent, Selective, and Orally Bioavailable IRAK4 PROTAC Degrader for the Treatment of Inflammatory Diseases.

Journal of medicinal chemistry·2026

Same author

Collaborative Diagnosis of Spatiotemporal Faults and Sensor Anomalies in Parabolic Distributed Parameter Systems.

IEEE transactions on cybernetics·2026

Same author

Adaptive Sensor Fault-Tolerant Control for Distributed Parameter Systems.

IEEE transactions on cybernetics·2026

Same author

Adaptive Neural Network-Based Fault Detection for Thermal Process of Battery Cells.

IEEE transactions on cybernetics·2026

Same author

Fuzzy Intermittent Control for Nonlinear Coupled Delayed PDE-ODE Systems.

IEEE transactions on cybernetics·2025

Same author

Dual Event-Triggered Spatial Model Predictive Control for Distributed Thermal Processes.

IEEE transactions on cybernetics·2025

Search research articles

Related Experiment Video

Updated: Jan 5, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Mixed Maximum Loss Design for Optic Disc and Optic Cup Segmentation with Deep Learning from Imbalanced Samples.

Yong-Li Xu¹, Shuai Lu², Han-Xiong Li^3,4

¹Department of Mathematics, Beijing University of Chemical Technology, Beijing 100029, China. xuyongli2312@sina.com.

Sensors (Basel, Switzerland)

|October 17, 2019

Summary

Accurate glaucoma screening relies on segmenting optic disc (OD) and optic cup (OC). A novel deep learning model, MSMKU, with a unique training strategy, achieves state-of-the-art results in OD and OC segmentation for early glaucoma detection.

Keywords:

convolutional neural network glaucoma screening mixed maximum loss minimization optic cup segmentation optic disc segmentation

More Related Videos

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

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

Published on: April 11, 2025

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

Related Experiment Videos

Last Updated: Jan 5, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: April 11, 2025

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Glaucoma is a leading cause of irreversible blindness.
Early diagnosis is crucial for effective glaucoma management.
Accurate segmentation of optic disc (OD) and optic cup (OC) in fundus images is vital for glaucoma screening.

Purpose of the Study:

To develop an accurate and robust method for OD and OC segmentation in fundus images.
To improve automated glaucoma screening through enhanced image analysis.

Main Methods:

A novel U-shaped convolutional neural network, termed MSMKU (multi-scale input and multi-kernel modules), was designed for OD and OC segmentation.
MSMKU features a rich receptive field and effective multi-scale feature representation.
A mixed maximum loss minimization learning strategy (MMLM) was developed for training, adaptively re-weighting samples to improve overall prediction performance.

Main Results:

The proposed MSMKU method achieved state-of-the-art breakthrough results for OD and OC segmentation on the RIM-ONE-V3 and DRISHTI-GS datasets.
The method demonstrated satisfactory glaucoma screening performance on these datasets.
MSMKU outperformed existing deep learning methods in accuracy, particularly on datasets with imbalanced sample distributions.

Conclusions:

The developed MSMKU model and MMLM training strategy offer a significant advancement in automated glaucoma screening.
Accurate OD and OC segmentation using this deep learning approach can enhance early detection and management of glaucoma.
This method shows promise for improving diagnostic accuracy in clinical settings, especially with challenging, imbalanced datasets.