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

Deep Unsupervised Domain Adaptation for Translating Cancer Dependency Maps From Cell Lines to Breast Cancer Tumor Genomics.

Genetic epidemiology·2026

Same author

Generative AI for the Design of Molecules: Advances and Challenges.

Journal of chemical information and modeling·2025

Same author

MolGraph-xLSTM as a graph-based dual-level xLSTM framework for enhanced molecular representation and interpretability.

Communications chemistry·2025

Same author

A national atlas to improve the study of Canadians living with long COVID (post-COVID-19 condition).

Canadian journal of public health = Revue canadienne de sante publique·2025

Same author

Enhanced Interpretable Neural Network Approach for Unified Batch Effect Mitigation and Disease Classification Using Cross-Cohort Microbiome Profiles.

Journal of computational biology : a journal of computational molecular cell biology·2025

Same author

GraphBAN: An inductive graph-based approach for enhanced prediction of compound-protein interactions.

Nature communications·2025

Search research articles

Related Experiment Video

Updated: Sep 1, 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

Semi-supervised COVID-19 CT image segmentation using deep generative models.

Judah Zammit¹, Daryl L X Fung¹, Qian Liu^1,2

¹Department of Computer Science, University of Manitoba, Winnipeg, MB, R3T 2N2, Canada.

BMC Bioinformatics

|August 16, 2022

Summary

This summary is machine-generated.

This study introduces StitchNet, a novel semi-supervised learning model for segmenting lung CT images in COVID-19 patients. StitchNet effectively addresses the challenge of limited labeled data in medical image analysis.

Keywords:

COVID-19 Computed tomography Convolutional network Image segmentation Semi-supervised learning

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Sep 1, 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

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical Imaging
Artificial Intelligence
Computational Biology

Background:

Limited labeled data is a significant challenge in medical image segmentation, particularly for Coronavirus Disease 2019 (COVID-19) lung CT scans.
The scarcity of labeled data stems from the recent emergence of COVID-19, hindering the generation of extensive annotated datasets.
Semi-supervised learning offers a promising approach to leverage unlabeled data, but its application to image segmentation is complex.

Purpose of the Study:

To bridge the gap between the need for accurate medical image segmentation and the scarcity of labeled data.
To develop a novel model combining deep convolutional networks for image segmentation and generative models for semi-supervised learning.
To specifically address the segmentation of lung CT images from COVID-19 patients.

Main Methods:

Proposing a novel generative model named the shared variational autoencoder (SVAE).
Implementing a five-layer deep hierarchy of latent variables with deep convolutional mappings within the SVAE.
Introducing a novel component in the SVAE's final layer to enforce reconstruction matching ground truth segmentation when available, resulting in the StitchNet model.

Main Results:

StitchNet demonstrated comparable performance to existing image segmentation models on a high-quality dataset of COVID-19 patient CT images.
The proposed model effectively utilizes semi-supervised learning principles for medical image segmentation.
The study validates the potential of generative models in addressing data scarcity in medical imaging.

Conclusions:

StitchNet offers a viable solution for segmenting lung CT images in the context of limited labeled data.
The research explores the advantages and limitations of the proposed StitchNet algorithm.
Future research directions are proposed to further advance semi-supervised learning in medical image segmentation for challenging cases like COVID-19.