Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Cross-prescription validation of knowledge-based planning in prostate VMAT using a structured validation framework.

Medical dosimetry : official journal of the American Association of Medical Dosimetrists·2026

Same author

Calibration of diffusion MRI measurements using aqueous glycerin phantoms with controlled viscosity.

Radiological physics and technology·2026

Same author

A structural tissue water fraction phantom derived from electron microscopy for simulation-based evaluation in MRI.

Magma (New York, N.Y.)·2026

Same author

Comprehensive Study on Quantitative Evaluation of Oral Muscle Tissue in Children With Low Tongue Posture Using Cone Beam Computed Tomography: A Comprehensive Study on Nasal Ventilation Conditions Using Computational Fluid Dynamics.

Journal of oral rehabilitation·2026

Same author

Systematic comparison of manual, knowledge-based, and feasibility DVH approaches for prostate VMAT: stability and robustness.

Physical and engineering sciences in medicine·2026

Same author

Comparison of long-term outcomes between proximal gastrectomy and total gastrectomy for advanced gastric cancer in the upper third of the stomach: a propensity score-matched analysis.

Japanese journal of clinical oncology·2026

Search research articles

Related Experiment Video

Updated: Oct 23, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Automatic contour segmentation of cervical cancer using artificial intelligence.

Yosuke Kano¹, Hitoshi Ikushima², Motoharu Sasaki²

¹Department of Radiological Technology, Tokushima Prefecture Naruto Hospital, 32 Kotani, Muyacho, Kurosaki, Naruto-shi, Tokushima 772-8503, Japan.

Journal of Radiation Research

|August 17, 2021

Summary

Automatic segmentation of cervical cancer tumors using U-Net models aids radiation oncologists. This study shows high accuracy in delineating tumor contours from diffusion-weighted images, reducing manual workload.

Keywords:

Dice similarity coefficient (DSC)automatic tumor contour segmentation cervical cancer diffusion-weighted imaging (DWI)radiation therapy

More Related Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Artificial Intelligence Approaches to Assessing Primary Cilia

Artificial Intelligence Approaches to Assessing Primary Cilia

Published on: May 1, 2021

Related Experiment Videos

Last Updated: Oct 23, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Artificial Intelligence Approaches to Assessing Primary Cilia

Artificial Intelligence Approaches to Assessing Primary Cilia

Published on: May 1, 2021

Area of Science:

Medical Imaging
Oncology
Artificial Intelligence

Background:

Radiation therapy for cervical cancer requires accurate tumor contour delineation by oncologists.
Manual contouring is time-consuming and can be burdensome.
Automatic segmentation methods are rarely applied to cervical cancer treatment.

Purpose of the Study:

To investigate the feasibility of automatic tumor contour segmentation in cervical cancer using deep learning.
To develop and evaluate a U-Net based model for segmenting cervical cancer tumors on diffusion-weighted images (DWI).

Main Methods:

Trained 2D and 3D U-Net models on DWI from 98 cervical cancer patients.
Employed cross-validation by swapping training and test datasets.
Generated final segmentation by summing and binarizing six prediction images per case.
Evaluated performance using Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD).

Main Results:

The automatic segmentation achieved a median DSC of 0.83 (mean 0.77), indicating high accuracy.
Hausdorff Distance ranged from 2.7 to 9.6 mm (median 4.7 mm).
Lower accuracy (DSC <0.65) was observed in smaller tumors (<40 mm) with necrosis.

Conclusions:

Automatic tumor contour segmentation for cervical cancer is feasible with high accuracy.
This AI-driven approach shows potential to reduce the workload for radiation oncologists.
Further refinement may improve segmentation for challenging cases like necrotic tumors.