Search research articles

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

Retinal graph neural network for segmentation of retinal vasculature and foveal avascular zone from OCTA images.

Biomedizinische Technik. Biomedical engineering·2026

Same author

Dual-Modal Deep Learning with In-Domain Training and Attention for Infant Brain Myelination Prediction.

Neuroinformatics·2026

Same author

Investigating Gen Z's equity investment intentions through a novel integrated psychological framework: An empirical validation.

Acta psychologica·2026

Same author

Ecological risk and source attribution of macro litter in the biodiverse blue carbon mangrove ecosystem along the Gulf of Mannar.

Marine pollution bulletin·2025

Same author

Spatial variation and pollution indices of anthropogenic marine litter on the beaches in gulf of Mannar, India.

Marine pollution bulletin·2025

Same author

Enhanced photocatalytic dye detoxification by banana peel derived enzyme inherited ZnO/g-C<sub>3</sub>N<sub>4</sub> nanocomposite: Validation by soil health and seed germination analyses.

International journal of biological macromolecules·2025

Same journal

CNN models in time-frequency domain for identification of motor imagery tasks from EEG signals.

Physical and engineering sciences in medicine·2026

Same journal

Radiomic correlates with overall survival in glioblastoma: amide proton transfer (APT) imaging-based feature analysis and integration of clinical factors.

Physical and engineering sciences in medicine·2026

Same journal

In radiation oncology, the best way to maintain patient safety when implementing cutting edge technologies such as AI-based and real-time adaptive techniques is through prospective hazard analysis.

Physical and engineering sciences in medicine·2026

Same journal

Compact neural network algorithm for electrocardiogram classification.

Physical and engineering sciences in medicine·2026

Same journal

Fat-suppression performance for in-stent plaque imaging after carotid artery stenting using three-dimensional T<sub>1</sub>-weighted MRI: a phantom study.

Physical and engineering sciences in medicine·2026

Same journal

Deep learning based depth of anaesthesia monitoring using EEG: a 4-layer CNN model with PSD and BSR correlation features.

Physical and engineering sciences in medicine·2026

See all related 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

Search research articles

Related Experiment Video

Updated: Aug 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

Deep learning approaches based improved light weight U-Net with attention module for optic disc segmentation.

R Shalini¹, Varun P Gopi²

¹Department of Electronics and Communication Engineering, National Institute of Technology, Tiruchirappalli, Tamilnadu, 620015, India.

Physical and Engineering Sciences in Medicine

|September 12, 2022

Summary

This summary is machine-generated.

This study introduces an enhanced U-Net model for segmenting optic disc images, crucial for early glaucoma detection. The model achieves high accuracy with reduced parameters and fast inference times, aiding in glaucoma screening.

Keywords:

Attention U-Net Deep learning EfficientNet Optic disc Transfer learning segmentation

More Related Videos

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

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

Published on: December 15, 2023

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: Aug 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

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

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

Published on: December 15, 2023

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
Computer Science

Background:

Glaucoma is a leading cause of global blindness, necessitating early detection for effective management.
Optic disc (OD) size variations can indicate glaucoma-induced optic nerve head anomalies.
Accurate OD segmentation is vital for glaucoma screening and diagnosis.

Purpose of the Study:

To propose an enhanced lightweight U-Net model with an Attention Gate (AG) for improved optic disc (OD) segmentation.
To leverage transfer learning with EfficientNet-B0 for feature extraction and mitigate gradient vanishing and overfitting.
To enhance segmentation accuracy using a binary focal loss function.

Main Methods:

Developed an enhanced lightweight U-Net model incorporating an Attention Gate (AG).
Employed transfer learning with a pre-trained EfficientNet-B0 Convolutional Neural Network (CNN).
Utilized a binary focal loss function for neural network training.

Main Results:

The proposed model achieved significant parameter reduction (approx. 0.53 M).
Demonstrated fast inference times: 40.3 ms (DRIONS-DB), 44.2 ms (DRISHTI-GS), and 60.6 ms (MESSIDOR).
Validated the pre-trained Attention U-Net on public datasets (DRIONS-DB, DRISHTI-GS, MESSIDOR).

Conclusions:

The enhanced U-Net model offers an efficient and accurate solution for optic disc segmentation.
This approach shows promise for computer-aided diagnosis in early glaucoma detection.
The model's lightweight design and fast inference are suitable for clinical screening applications.