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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Human Activity Recognition with Noise-Injected Time-Distributed AlexNet.

Biomimetics (Basel, Switzerland)·2025
Same author

An open-source repository-based tool for quality control of imaging protocol compliance: demonstration in a multicentre MRI study.

The British journal of radiology·2025
Same author

Weakly supervised pathological differentiation of primary central nervous system lymphoma and glioblastoma on multi-site whole slide images.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Image quality in whole-body MRI using the MY-RADS protocol in a prospective multi-centre multiple myeloma study.

Insights into imaging·2023
Same author

A systematic review of the prediction of hospital length of stay: Towards a unified framework.

PLOS digital health·2023
Same author

Implementation of Whole-Body MRI (MY-RADS) within the OPTIMUM/MUKnine multi-centre clinical trial for patients with myeloma.

Insights into imaging·2022

Related Experiment Video

Updated: Oct 22, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

13.0K

Investigating the Performance of Generative Adversarial Networks for Prostate Tissue Detection and Segmentation.

Ufuk Cem Birbiri1, Azam Hamidinekoo2, Amélie Grall3

  • 1Department of Computer Engineering, Middle East Technical University, Ankara 06800, Turkey.

Journal of Imaging
|August 30, 2021
PubMed
Summary
This summary is machine-generated.

Conditional generative adversarial networks (cGANs) improve prostate tissue segmentation in 3D MRI scans, outperforming other models for better region of interest (RoI) definition in clinical applications.

Keywords:
computer aided diagnosisdetectiongenerative adversarial networkprostate MRIsegmentation

More Related Videos

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

788
Generation of Tumor Organoids from Genetically Engineered Mouse Models of Prostate Cancer
08:54

Generation of Tumor Organoids from Genetically Engineered Mouse Models of Prostate Cancer

Published on: June 13, 2019

10.8K

Related Experiment Videos

Last Updated: Oct 22, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

13.0K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

788
Generation of Tumor Organoids from Genetically Engineered Mouse Models of Prostate Cancer
08:54

Generation of Tumor Organoids from Genetically Engineered Mouse Models of Prostate Cancer

Published on: June 13, 2019

10.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Manual delineation of the region of interest (RoI) in 3D MRI prostate scans is time-consuming and subjective.
  • Accurate prostate tissue identification is crucial for Computer-Aided Detection (CAD) systems in diagnostics, radiotherapy, and disease monitoring.

Purpose of the Study:

  • To evaluate the performance of Conditional GAN (cGAN), cycleGAN, and U-Net models for prostate tissue detection and segmentation in 3D multi-parametric MRI.
  • To investigate the impact of data augmentation techniques on model performance with limited training data.

Main Methods:

  • Training and evaluation of cGAN, cycleGAN, and U-Net models on 3D multi-parametric MRI data from 40 prostate cancer patients.
  • Implementation of three data augmentation schemes to increase the size of the training dataset.
  • Testing models on a private clinical dataset and the public PROMISE12 dataset.

Main Results:

  • The cGAN model demonstrated superior performance compared to U-Net and cycleGAN, attributed to the use of paired image supervision.
  • cGAN achieved a Dice score of 0.78 on the private dataset and 0.75 on the PROMISE12 public dataset.

Conclusions:

  • Conditional GANs offer a promising approach for automated and accurate prostate tissue segmentation in 3D MRI.
  • The developed cGAN model can enhance the precision of region of interest (RoI) definition for clinical applications in prostate cancer management.