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

Search research articles

Related Experiment Video

Updated: Jan 18, 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

Leveraging Deep Learning to Address Diagnostic Challenges with Insufficient Image Data.

Jian-Ming Lu¹, Ping-Yeh Chiu^1,2, Chien-Fu Chen^1,3

¹Institute of Applied Mechanics, National Taiwan University, Taipei 106, Taiwan.

|September 11, 2025

Summary

This summary is machine-generated.

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

Biomechanical Impact of Footprint Mismatch and Implant Positioning in Cervical Disk Replacement: A Finite Element Analysis.

Operative neurosurgery (Hagerstown, Md.)·2026

Same author

Ultra-Sensitive 3D Lateral Flow Assay Device for SARS-CoV-2 Detection Based on One-Step Dual-Signal Amplification.

Analytical chemistry·2025

Same author

Effects of erector spinae plane block on intraoperative blood pressure variability, blood loss, and postoperative pain in transforaminal lumbar interbody fusion.

Scientific reports·2025

Same author

Optimizing Rod Configuration Across Lumbar Pedicle Subtraction Osteotomy Site: Evolution of a High-Volume Deformity Practice.

Operative neurosurgery (Hagerstown, Md.)·2025

Same author

What is the best strategy for C3 in open-door laminoplasty: laminectomy versus laminoplasty-a systematic review and meta-analysis.

The spine journal : official journal of the North American Spine Society·2025

Same author

Minimally invasive prone lateral retropleural or retroperitoneal antepsoas approach spinal surgery using the rotatable radiolucent Jackson table.

Journal of spine surgery (Hong Kong)·2025

Same journal

Multimodal Detection of Low Water Contents in Ethanol Using a Plasmon-Berreman-Enhanced Metasurface Infrared Absorber.

ACS sensors·2026

Same journal

3D-Printed Hollow Microneedle Potentiometric Sensors: A Modular Approach.

ACS sensors·2026

Same journal

A Genetically Encoded Fluorescent Sensor for Protein Arginine Phosphorylation.

ACS sensors·2026

Same journal

Single-Atom Ni-Modified SnO<sub>2</sub> for Ultrasensitive NO<sub>2</sub> Gas Sensing through Enhanced Molecular Adsorption and Efficient Charge Transfer.

ACS sensors·2026

Same journal

Harnessing Thermoelectric-Mediated Photoelectrochemical System to Address Sensitive Dopamine Detection via APE1-Amplified Triple-Helix Switching.

ACS sensors·2026

Same journal

Ultrasensitive Detection of Mold Biomarker 1-Octen-3-ol Using AuPt Nanocluster-Sensitized WO<sub>3</sub> Gas Sensor for On-Site Grain Safety Monitoring.

ACS sensors·2026

See all related articles

This study introduces a novel AI model, DSAWGAN, for infectious disease diagnosis with limited data. It significantly boosts diagnostic accuracy, making it effective for resource-limited settings.

Area of Science:

Artificial Intelligence
Medical Diagnostics
Bioinformatics

Background:

AI-driven disease diagnosis relies heavily on large datasets and advanced algorithms.
Generating comprehensive datasets for rare or emerging diseases is challenging.
Limited data availability hinders AI model performance in diagnostics.

Purpose of the Study:

To introduce a Direct-Self-Attention Wasserstein Generative Adversarial Network (DSAWGAN) for improved infectious disease diagnosis.
To enhance diagnostic capabilities in scenarios with limited data.
To develop a portable and cost-effective diagnostic solution.

Main Methods:

Developed DSAWGAN by integrating attention modules and Wasserstein distance optimization.
Compared DSAWGAN-generated images against traditional data augmentation techniques.

Keywords:

artificial intelligence data augmentation generative adversarial networks lateral flow immunoassay test point of care

Related Experiment Videos

Last Updated: Jan 18, 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

Evaluated diagnostic accuracy using classification neural networks.

Integrated the model into a mobile application for portable testing.

Main Results:

DSAWGAN improved diagnostic accuracy from 98.00% to 99.33% using only half the raw data (n=1500).
Even with 10% of the data (n=300), the model maintained 92.67% accuracy.
The generated images showed enhanced convergence speed, stability, and quality.

Conclusions:

DSAWGAN effectively addresses data scarcity in AI-driven disease diagnosis.
The model offers a viable solution for rapid, portable, and cost-effective diagnostics.
This approach shows significant promise for resource-limited healthcare settings.