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 8, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

Automatic contouring system for cervical cancer using convolutional neural networks.

Dong Joo Rhee1,2, Anuja Jhingran3, Bastien Rigaud4

  • 1MD Anderson UTHealth Graduate School, Houston, TX, USA.

Medical Physics
|September 23, 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

Artificial Intelligence in Image Assisted Radiation Oncology.

Cancers·2026
Same author

Assessing predictors of brachytherapy utilization among cervical cancer patients in Nigeria: evidence from a tertiary cancer centre.

BMC cancer·2026
Same author

Use of Large Language Models to Enhance Failure Mode and Effects Analysis: A Case Study.

Advances in radiation oncology·2026
Same author

A New Remote Classroom Approach to Contouring Training for Pelvic Malignancies in Low- to Middle-Income Asian Countries.

Cureus·2026
Same author

Parallel/Opposed: Automated treatment planning systems should be designed to minimize human intervention.

Journal of applied clinical medical physics·2026
Same author

AI-based framework to fuse pre-RT brain metastases contours with follow-up MRI to improve post-RT assessment.

Neuro-oncology practice·2026
This summary is machine-generated.

This study developed an AI tool using convolutional neural networks (CNNs) for automatic contouring in cervical cancer radiotherapy. The CNN tool accurately delineates clinical treatment volumes and normal tissues, achieving high clinical acceptability.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiotherapy

Background:

  • Accurate delineation of clinical treatment volumes (CTVs) and organs at risk (OARs) is crucial for effective radiotherapy planning in cervical cancer.
  • Manual contouring is time-consuming and subject to inter-observer variability.

Purpose of the Study:

  • To develop and validate a convolutional neural network (CNN)-based auto-contouring tool for cervical cancer radiotherapy.
  • To improve the efficiency and consistency of treatment planning by automating the delineation of CTVs and normal tissues.

Main Methods:

  • A CNN-based auto-contouring tool was developed to delineate three cervical CTVs and 11 normal structures (seven OARs, four bony structures).
  • The tool was trained and validated using 2254 retrospective CT scans from a single center and 210 scans from a segmentation challenge.
Keywords:
auto-contouringcervical cancerconvolutional neural networkdeep learning

Related Experiment Videos

Last Updated: Dec 8, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K
  • Accuracy was assessed using Sørensen-dice similarity coefficient (DSC) and surface/Hausdorff distances on 140 internal scans, and clinical acceptability was evaluated by a radiation oncologist on 30 external scans.

    • Main Results:

    • The CNN tool achieved high accuracy, with average DSC values ranging from 0.76 to 0.95 for different structures.
    • Mean surface distances ranged from 0.05 cm to 0.27 cm, and Hausdorff distances ranged from 0.53 cm to 2.09 cm.
    • Clinical evaluation showed that 80% of CTVs, 97% of OARs, and 98% of bony structures were deemed clinically acceptable on external datasets.

    Conclusions:

    • The developed CNN-based auto-contouring tool demonstrates strong performance on both internal and external datasets.
    • The tool achieved a high rate of clinical acceptability, indicating its potential for routine use in cervical cancer radiotherapy planning.
    • This automated approach can significantly streamline the radiotherapy planning process, potentially improving treatment outcomes.