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: Oct 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized

Zhikai Liu1, Wanqi Chen2, Hui Guan1

  • 1Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Frontiers in Oncology
|September 7, 2021
PubMed

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

Fabrication of sulfobutylether-β-cyclodextrin/glabridin inclusion complex for promoting bioactivities.

Archiv der Pharmazie·2024
Same author

Ring artifacts removal in X-ray-induced acoustic computed tomography.

Journal of innovative optical health sciences·2024
Same author

Investigation on Mechanism of Microstructure Evolution during Multi-Process Hot Forming of GH4169 Superalloy Forging.

Materials (Basel, Switzerland)·2024
Same author

Xiebai San alleviates acute lung injury by inhibiting the phosphorylation of the ERK/Stat3 pathway and regulating multiple metabolisms.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2024
Same author

Pharmacological effects and target analysis of Guipi wan in the treatment of cerebral ischemia-reperfusion injury.

Frontiers in pharmacology·2024
Same author

Toxicity of urban stormwater on Chlorella pyrenoidosa: Implications for reuse safety.

The Science of the total environment·2024
Summary

A novel deep learning model for cervical cancer auto-segmentation achieved accuracy comparable to manual delineation. This artificial intelligence (AI) approach shows promise for improving clinical workflows in radiation oncology.

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Accurate delineation of the clinical target volume (CTV) is crucial for effective cervical cancer radiotherapy.
  • Manual CTV segmentation is time-consuming and subject to inter-observer variability.
  • Deep learning offers potential for automated and consistent segmentation.

Purpose of the Study:

  • To develop and validate a novel deep-learning-based auto-segmentation model for CTV delineation in cervical cancer.
  • To evaluate the performance of the AI model against manual delineation using a rigorous three-stage multicenter framework.

Main Methods:

  • An adversarial deep learning model was trained on CT data from 237 cervical cancer patients.
  • A three-stage multicenter evaluation was conducted with 9 oncologists from 6 institutions using CT scans from 20 patients.
Keywords:
auto-segmentationcervical cancerclinical target volumedeep-learningevaluationradiotherapy

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

274

Related Experiment Videos

Last Updated: Oct 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

274
  • Evaluation included objective metrics (DSC, 95HD), oncologist grading, and a Turing imitation test.

    • Main Results:

    • The AI model achieved a mean Dice Similarity Coefficient (DSC) of 0.88 and a 95% Hotelling's T-squared (95HD) value of 3.46 mm.
    • Oncologist assessments indicated AI contours were comparable to ground truth (GT) contours, with no significant statistical differences in CTV scores.
    • In the Turing test, 60.0% of AI contours were judged superior to GT contours by at least 5 oncologists in week 0.

    Conclusions:

    • The developed AI model demonstrates accuracy and comparability to manual CTV segmentation in cervical cancer.
    • The three-stage evaluation framework provides a robust assessment of AI performance in clinical settings.
    • This AI model has the potential to enhance efficiency and consistency in cervical cancer radiotherapy planning.