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

MRI- and report-based multimodal model with SHAP-based explanation for preoperative prediction of deep stromal invasion in early-stage cervical cancer.

Insights into imaging·2026
Same author

A deep learning-driven automated treatment planning framework for cervical cancer patients treated with volumetric modulated arc therapy.

Radiation oncology (London, England)·2026
Same author

Deep learning and dual-radiomics model incorporating brachytherapy applicator type to predict radiation-induced acute rectal injury in cervical cancer patients.

Physics and imaging in radiation oncology·2026
Same author

Prescribed-Time Distributed Integral Sliding-Mode-Based Least-Norm Nash Equilibrium Seeking in Monotone Games Under Disturbances.

IEEE transactions on cybernetics·2025
Same author

Automatic radiotherapy planning for deliverable plans using deep learning dose prediction and dose rings optimization in cervical cancer.

Journal of applied clinical medical physics·2025
Same author

Integrating Deep Learning and Radiomics in Differentiating Papillary Thyroid Microcarcinoma from Papillary Thyroid Carcinoma with Ultrasound Images.

Cancer management and research·2025

Related Experiment Video

Updated: Jun 5, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K

Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN.

Zeshuo Zhao1, Yuning Qin2, Kai Shao1

  • 1Department of Radiotherapy Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.

Technology in Cancer Research & Treatment
|December 6, 2024
PubMed
Summary
This summary is machine-generated.

CycleGAN style transfer harmonizes ultrasound radiomics, improving lymph node metastasis prediction in early cervical cancer patients. This technique enhances image consistency across different scanners for better diagnostic accuracy.

Keywords:
generative adversarial networksharmonizationlymph node metastasisradiomicsultrasound

More Related Videos

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.4K

Related Experiment Videos

Last Updated: Jun 5, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.4K

Area of Science:

  • Medical imaging
  • Artificial intelligence
  • Oncology

Background:

  • Ultrasound (US) radiomics are prone to variations from different scanners and sonographers.
  • Standardizing US images is crucial for reliable radiomics analysis.

Purpose of the Study:

  • To assess the feasibility of CycleGAN for style transfer to enhance US radiomics.
  • To improve lymph node metastasis (LNM) prediction in early cervical cancer (ECC) using harmonized US images from multiple scanners.

Main Methods:

  • CycleGAN was trained on phantom and clinical US images of ECC patients.
  • The model performed style transfer to harmonize images from four different US devices to a single domain.
  • Radiomics features were extracted, and LNM prediction model performance was evaluated.

Main Results:

  • Phantom studies showed improved radiomics harmonization (Pearson's r: 0.60 to 0.81) and image quality (PSNR: 11.18 to 15.45).
  • The area under the curve (AUC) for LNM prediction improved from 0.78 (original images) to 0.85 (style-transferred images).
  • Style-transferred images from different models yielded AUCs ranging from 0.73 to 0.85.

Conclusions:

  • Adapted CycleGAN effectively harmonizes US radiomics features across different equipment.
  • Style transfer improves LNM prediction accuracy in early cervical cancer patients.