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

Nanomechanical Characterization of Plasma-Sprayed Nanostructured Yb<sub>4</sub>Hf<sub>3</sub>O<sub>12</sub> Thermal/Environmental Barrier Coatings.

Materials (Basel, Switzerland)·2026
Same author

Prognostic value of preoperative CT-derived fractional flow reserve after transcatheter or surgical aortic valve replacement in patients with severe aortic stenosis.

BMC medical imaging·2026
Same author

Hydrogenation of α- and β-Keto Esters under Atmospheric Pressure Catalyzed by a Metal-Ligand Bifunctional Iridium Catalyst.

The Journal of organic chemistry·2026
Same author

Computed Tomography-Based Radiomics Provides New Insights Into Associations Between Pericoronary Fat Characteristics and Low-Density Lipoprotein Cholesterol.

Reviews in cardiovascular medicine·2026
Same author

Lower deep-to-superficial extensor muscle ratio (DSR) as an independent risk factor for early titanium implant subsidence following single-level anterior cervical corpectomy and fusion.

Neurosurgical review·2026
Same author

Incidence and Management of Cerebrospinal Fluid Leakage due to Late Presentation of Dural Tears After Lumbar Surgery.

Orthopaedic surgery·2026

Related Experiment Video

Updated: Nov 12, 2025

Surgical Model for Single-Staged Tissue-Engineered Urothelial Tubes in Minipigs
04:05

Surgical Model for Single-Staged Tissue-Engineered Urothelial Tubes in Minipigs

Published on: July 5, 2024

493

Synthetic CT Generation of the Pelvis in Patients With Cervical Cancer: A Single Input Approach Using Generative

Atallah Baydoun1, K E Xu2,3, Jin Uk Heo4,5

  • 1Department of Radiation Oncology, University Hospitals Cleveland Medical Center, Cleveland, OH 44106, USA.

IEEE Access : Practical Innovations, Open Solutions
|March 22, 2021
PubMed
Summary

A new deep learning framework, sU-cGAN, generates synthetic CT images from MR scans for cervical cancer patients. This approach improves precision medicine by reducing radiation exposure and costs associated with multi-modality imaging.

Keywords:
Cervical cancerU-Netcomputed tomographydeep learninggenerative adversarial networkmagnetic resonance imaging

More Related Videos

Generation of Prostate Cancer Patient Derived Xenograft Models from Circulating Tumor Cells
08:03

Generation of Prostate Cancer Patient Derived Xenograft Models from Circulating Tumor Cells

Published on: October 20, 2015

14.4K
Generation of an Orthotopic Xenograft of Pancreatic Cancer Cells by Ultrasound-Guided Injection
05:49

Generation of an Orthotopic Xenograft of Pancreatic Cancer Cells by Ultrasound-Guided Injection

Published on: November 1, 2021

3.4K

Related Experiment Videos

Last Updated: Nov 12, 2025

Surgical Model for Single-Staged Tissue-Engineered Urothelial Tubes in Minipigs
04:05

Surgical Model for Single-Staged Tissue-Engineered Urothelial Tubes in Minipigs

Published on: July 5, 2024

493
Generation of Prostate Cancer Patient Derived Xenograft Models from Circulating Tumor Cells
08:03

Generation of Prostate Cancer Patient Derived Xenograft Models from Circulating Tumor Cells

Published on: October 20, 2015

14.4K
Generation of an Orthotopic Xenograft of Pancreatic Cancer Cells by Ultrasound-Guided Injection
05:49

Generation of an Orthotopic Xenograft of Pancreatic Cancer Cells by Ultrasound-Guided Injection

Published on: November 1, 2021

3.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Multi-modality imaging is crucial for precision medicine in oncology, particularly for cervical cancer diagnosis and treatment planning.
  • Current methods using PET, MR, and CT imaging require co-registration, which can lead to defects, increased costs, and radiation exposure.

Purpose of the Study:

  • To develop a novel framework for cross-modality image synthesis to overcome limitations of traditional multi-modality imaging in cervical cancer.
  • To apply a conditional generative adversarial network (cGAN) for MR-CT image translation, enabling accurate synthetic CT (sCT) generation.

Main Methods:

  • The proposed framework, sU-cGAN, utilizes a shallow U-Net (sU-Net) with an encoder/decoder depth of 2 as the generator.
  • The input for sU-cGAN is T2-weighted, Turbo Spin Echo Single Shot (TSE-SSH) MR images, commonly used for radiological diagnosis.
  • The study addresses the vanishing gradient and feature extraction challenges in deep learning for image synthesis.

Main Results:

  • sU-cGAN successfully generates accurate synthetic CT (sCT) images from MR images for cervical cancer diagnosis and treatment.
  • The framework demonstrates superior performance compared to other state-of-the-art deep learning methods, even with limited training data and a single input channel.
  • The approach offers a simpler yet efficient solution for MR-CT image translation.

Conclusions:

  • The sU-cGAN framework presents a promising advancement in cross-modality image synthesis for cervical cancer precision oncology.
  • The study suggests further clinical investigation of this framework is warranted.
  • The developed sU-Net model shows potential for application in other computer vision tasks.