Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Dec 25, 2025

Generation of Self-assembled Vascularized Human Skin Equivalents
09:04

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

7.1K

CTumorGAN: a unified framework for automatic computed tomography tumor segmentation.

Shuchao Pang1, Anan Du2, Mehmet A Orgun3,4

  • 1Department of Computing, Macquarie University, Sydney, NSW, 2109, Australia.

European Journal of Nuclear Medicine and Molecular Imaging
|March 31, 2020
PubMed
Summary

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

Weight-Adjusted-Waist Index and Cognitive Function: Beyond Inflammatory Mediation Alone.

Geriatrics & gerontology international·2026
Same author

Plasma Pentosidine and Sarcopenia: Beyond Muscle Mass Alone.

Geriatrics & gerontology international·2026
Same author

An integrated above-belowground biological control strategy against Phyllotreta striolata using entomopathogenic nematodes and fungi.

Pest management science·2026
Same author

Multi-target mechanisms of Chinese herbal medicine in the treatment of allergic rhinitis.

Journal of ethnopharmacology·2026
Same author

Effect of Dry-Wet Cycling on Methanotrophs in Wetland Soils.

Biology·2026
Same author

Preliminary study on targeted therapy of breast cancer using tumor cell membrane-coated dual-loaded liposomes based on chemo-photothermal synergistic effects.

Drug delivery and translational research·2025
This summary is machine-generated.

This study introduces CTumorGAN, a novel framework for automatic tumor segmentation in CT scans. CTumorGAN effectively addresses challenges like low contrast and data variability, achieving competitive performance across diverse tumor types.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Automatic tumor segmentation in CT images is challenging due to low contrast, data variability, and similar visual characteristics between tumors and surrounding tissues.
  • Existing methods often struggle with generalization across different tumor datasets and modalities.
  • Tumor segmentation faces obstacles such as class imbalance, small tumor localization, and poor annotation quality.

Purpose of the Study:

  • To propose a novel, unified, and end-to-end adversarial learning framework for automatic segmentation of any tumor type from CT scans.
  • To address the limitations of current methods in handling diverse CT datasets and acquisition variations.
  • To improve the generalization capability of tumor segmentation models.

Main Methods:

Keywords:
Adversarial learningComputed tomography (CT)Conditional generative adversarial networks (cGAN)Loss functionTumor segmentation

More Related Videos

Preparing Porcine Eyes for Confocal Reflectance Microscopy to Visualize the Vitreous Collagen Fiber Network
06:07

Preparing Porcine Eyes for Confocal Reflectance Microscopy to Visualize the Vitreous Collagen Fiber Network

Published on: October 17, 2025

228
Author Spotlight: Enhanced Murine AAA Model Using Elastase to Mimic Human Aneurysms
07:42

Author Spotlight: Enhanced Murine AAA Model Using Elastase to Mimic Human Aneurysms

Published on: July 26, 2024

2.6K

Related Experiment Videos

Last Updated: Dec 25, 2025

Generation of Self-assembled Vascularized Human Skin Equivalents
09:04

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

7.1K
Preparing Porcine Eyes for Confocal Reflectance Microscopy to Visualize the Vitreous Collagen Fiber Network
06:07

Preparing Porcine Eyes for Confocal Reflectance Microscopy to Visualize the Vitreous Collagen Fiber Network

Published on: October 17, 2025

228
Author Spotlight: Enhanced Murine AAA Model Using Elastase to Mimic Human Aneurysms
07:42

Author Spotlight: Enhanced Murine AAA Model Using Elastase to Mimic Human Aneurysms

Published on: July 26, 2024

2.6K
  • Developed CTumorGAN, an adversarial learning framework comprising a Generator and a Discriminator network.
  • Incorporated specialized modules to handle class imbalance, small tumor localization, and label noise.
  • Utilized multi-level supervision to guide the training process effectively.

Main Results:

  • Identified Mean Square Error as a suitable loss function for CT tumor segmentation.
  • CTumorGAN demonstrated stable and competitive performance on lung, kidney, and liver tumor datasets.
  • Achieved superior results compared to state-of-the-art approaches in CT tumor segmentation.

Conclusions:

  • The proposed CTumorGAN framework effectively overcomes key challenges in CT tumor segmentation.
  • CTumorGAN exhibits superior performance and generalization capabilities across various tumor types and datasets.
  • This unified framework offers a promising solution for diverse clinical applications of automated tumor segmentation.