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

Appendiceal abscess mimicking a painless abdominal wall mass in an adolescent: a case report.

Frontiers in medicine·2026

Same author

Failed ultrasound-guided hydrostatic reduction in pediatric intussusception: surgical-pathological characterization of failure phenotypes under a standardized protocol.

Pediatric surgery international·2026

Same author

Inspired by sponge predation mechanisms: preparation of hydrogel adsorbents based on carboxymethyl konjac glucomannan for rapid removal of basic fuchsin and methylene blue.

International journal of biological macromolecules·2026

Same author

Laparoscopic intracavitary catheterization combined with bleomycin quadruple sclerotherapy for retroperitoneal lymphatic malformations: a single-center case series.

Frontiers in surgery·2026

Same author

Global, regional, and national burden of depression among women of childbearing age from 1990 to 2021: insights from the Global Burden of Disease Study 2021.

Archives of women's mental health·2026

Same author

Laparoscopic closure of the fascial defect combined with medial umbilical ligament reinforcement for incarcerated pediatric direct inguinal hernia: a case report with emergency management insights.

Frontiers in medicine·2026

Search research articles

Related Experiment Video

Updated: Sep 27, 2025

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

Augmentation-Consistent Clustering Network for Diabetic Retinopathy Grading with Fewer Annotations.

Guanghua Zhang¹, Keran Li², Zhixian Chen¹

¹Department of Intelligence and Automation, Taiyuan University, Taiyuan 030000, China.

Journal of Healthcare Engineering

|April 7, 2022

Summary

This study introduces an Augmentation-Consistent Clustering Network (ACCN) for diabetic retinopathy (DR) grading. The ACCN effectively utilizes unlabeled data to improve diagnostic accuracy with fewer expert annotations, addressing a key challenge in medical imaging.

More Related Videos

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

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Related Experiment Videos

Last Updated: Sep 27, 2025

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 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

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Area of Science:

Ophthalmology
Computer Science
Artificial Intelligence

Background:

Diabetic retinopathy (DR) is a leading cause of blindness.
Accurate DR grading is crucial for timely treatment.
Deep learning models for DR grading typically require extensive annotated data, which is costly and time-consuming to obtain.

Purpose of the Study:

To develop a semi-supervised deep learning model for diabetic retinopathy grading.
To reduce the reliance on large annotated datasets in DR grading.
To improve the efficiency and cost-effectiveness of DR diagnostic systems.

Main Methods:

Proposed an Augmentation-Consistent Clustering Network (ACCN).
Leveraged internal correlations within unlabeled fundus images.
Utilized augmentation strategies to provide similarity cues for unlabeled data.
Employed clustering techniques to discover subtle lesion features with limited annotations.

Main Results:

The ACCN demonstrated superior performance in semi-supervised DR grading.
The model effectively utilized unlabeled data to enhance diagnostic capabilities.
Achieved state-of-the-art results on the Messidor and APTOS 2019 datasets.
Showcased the ability to identify subtle lesion features with reduced annotation requirements.

Conclusions:

The ACCN offers a promising solution for semi-supervised diabetic retinopathy grading.
This approach significantly reduces the need for extensive expert annotations.
The method holds potential for more accessible and efficient DR screening tools.