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: Nov 21, 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

Distant Domain Transfer Learning for Medical Imaging.

Shuteng Niu, Meryl Liu, Yongxin Liu

IEEE Journal of Biomedical and Health Informatics

|January 15, 2021

Summary

This study introduces a novel transfer learning framework for COVID-19 diagnosis using lung CT scans. The method effectively utilizes unlabeled data from distant domains, achieving 96% accuracy.

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

Quantum-enhanced spiking intelligence framework for real-time anomaly detection in industrial internet of things.

Scientific reports·2026

Same author

BrainAuth: A Neuro-Biometric Approach for Personal Authentication.

IEEE journal of biomedical and health informatics·2025

Same author

Context-Driven Active Contour (CDAC): A Novel Medical Image Segmentation Method Based on Active Contour and Contextual Understanding.

Sensors (Basel, Switzerland)·2025

Same author

A Non-Invasive Blood Glucose Detection System Based on Photoplethysmogram With Multiple Near-Infrared Sensors.

IEEE journal of biomedical and health informatics·2024

Same author

Alzheimer's disease diagnosis in the metaverse.

Computer methods and programs in biomedicine·2024

Same author

Hash-MAC-DSDV: Mutual Authentication for Intelligent IoT-Based Cyber-Physical Systems.

IEEE internet of things journal·2023

Area of Science:

Artificial Intelligence
Medical Imaging
Computer Science

Background:

Medical image processing is crucial in the Internet of Medical Things (IoMT).
Deep learning achieves state-of-the-art results in medical imaging.
Access to labeled medical data, especially for novel diseases like COVID-19, is limited due to privacy concerns.

Purpose of the Study:

To propose a novel transfer learning framework for medical image classification, specifically for COVID-19 diagnosis using lung CT images.
To address the challenge of limited labeled data by leveraging unlabeled data from distant domains.
To investigate and develop a solution for Distant Domain Transfer Learning (DDTL).

Main Methods:

A novel transfer learning framework comprising a reduced-size Unet Segmentation model and a Distant Feature Fusion (DFF) classification model.

Related Experiment Videos

Last Updated: Nov 21, 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

Development of a DDTL model utilizing unlabeled datasets (Office-31, Caltech-256, chest X-ray) as source data.

Training the model with a small set of labeled COVID-19 lung CT images as target data.

Main Results:

Achieved 96% classification accuracy for COVID-19 diagnosis.
Demonstrated a 13% improvement over non-transfer algorithms.
Showed an 8% improvement over existing transfer and distant transfer algorithms.

Conclusions:

The proposed method effectively utilizes easily accessible unlabeled data from distant domains.
The framework successfully handles distribution shifts between training and testing data.
This approach offers a promising solution for medical image classification tasks with limited labeled data.