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

Safety and Efficacy of Ultra-Early Tirofiban Treatment Following Alteplase in Patients With Noncardioembolic Acute Ischemic Stroke.

Journal of the American Heart Association·2026

Same author

Pollution accumulation, sources, and risk assessment of potentially toxic elements in the soil-walnut system: insights from over 50 years of wastewater irrigation in a lead/zinc smelting region.

Environmental geochemistry and health·2026

Same author

Effects of ER-phagy regulatory genes on the microenvironment of hepatocellular carcinoma: a comprehensive analysis.

Discover oncology·2025

Same author

Mitochondrial autophagy-related lncRNAs as prognostic biomarkers and therapeutic targets in gastric adenocarcinoma.

Discover oncology·2025

Same author

MIST: Multi-instance selective transformer for histopathological subtype prediction.

Medical image analysis·2024

Same author

Prognostic correlation between specialized capillary endothelial cells and lung adenocarcinoma.

Heliyon·2024

Search research articles

Related Experiment Video

Updated: Dec 29, 2025

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

Multi-indices quantification of optic nerve head in fundus image via multitask collaborative learning.

Rongchang Zhao¹, Shuo Li²

¹School of Computer Science and Engineering, Central South University, Changsha, China; Hunan Engineering Research Center of Machine Vision and Intelligent Medicine, Changsha, China.

Medical Image Analysis

|November 16, 2019

Summary

This study introduces MCL-Net, a novel deep learning framework for precise optic nerve head (ONH) quantification from fundus images. MCL-Net achieves accurate multi-index ONH measurement, improving ophthalmic disease diagnosis, including glaucoma detection.

Keywords:

Collaborative learning Glaucoma diagnosis Multi-indices quantification Optic nerve head assessment

More Related Videos

Quantification of Optic Nerve Cross Sectional Area on MRI: A Novel Protocol using Fiji Software

Quantification of Optic Nerve Cross Sectional Area on MRI: A Novel Protocol using Fiji Software

Published on: September 4, 2021

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

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

Published on: August 4, 2018

Related Experiment Videos

Last Updated: Dec 29, 2025

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

Quantification of Optic Nerve Cross Sectional Area on MRI: A Novel Protocol using Fiji Software

Quantification of Optic Nerve Cross Sectional Area on MRI: A Novel Protocol using Fiji Software

Published on: September 4, 2021

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

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

Published on: August 4, 2018

Area of Science:

Ophthalmology and Medical Imaging
Artificial Intelligence in Healthcare
Computational Biology

Background:

Accurate optic nerve head (ONH) assessment is crucial for diagnosing ophthalmic diseases.
Simultaneous multi-indices quantification of the ONH from fundus images is clinically significant but challenging due to image variations and low contrast.
Existing methods lack comprehensive approaches for multi-indices ONH quantification.

Purpose of the Study:

To propose a novel multitask collaborative learning framework (MCL-Net) for accurate multi-indices ONH quantification.
To address the challenges of large variations, overlap, and weak contrast in fundus images for ONH assessment.
To improve the accuracy of ONH measurements and enhance diagnostic capabilities for ophthalmic diseases.

Main Methods:

Developed a two-branch neural network (MCL-Net) with shared and task-specific representations.
Implemented a feature interaction module (FIM) for collaborative feature exchange between network branches.
Utilized a multitask ensemble module (MEM) for automated aggregation of multiple output predictions.
Leveraged both segmentation and estimation tasks for comprehensive ONH quantification.

Main Results:

MCL-Net achieved accurate quantification of ONH diameters, whole areas, and regional areas with low mean absolute errors (e.g., 0.98 ± 0.20 for diameters).
High correlation coefficients (e.g., 0.699 for diameters) were observed between predicted and actual ONH indices.
Demonstrated improved glaucoma diagnosis with an Area Under the Curve (AUC) of 0.8698 using the quantitative indices from MCL-Net.

Conclusions:

MCL-Net effectively quantifies multiple ONH indices by collaboratively learning shared and task-specific representations.
The proposed framework significantly enhances the accuracy of ONH assessment compared to existing methods.
MCL-Net shows great potential for clinical application in ophthalmic disease diagnosis and assessment.