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

Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

63
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
63
Computed Tomography01:10

Computed Tomography

6.4K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Dependence of planning target volume margins on degrees of freedom and correlations of uncertainties.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026
Same author

Magnetic resonance imaging thoracic organ-at-risk atlas for radiation oncology.

Physics and imaging in radiation oncology·2026
Same author

Recommendations for contouring of gross tumour volume for locally advanced lung cancer using magnetic resonance imaging.

Physics and imaging in radiation oncology·2026
Same author

Cognitive Outcomes After Radiation Therapy for Medulloblastoma: A Voxel-based Analysis.

International journal of radiation oncology, biology, physics·2026
Same author

Empowering biological knowledgebases: advances in human-in-the-loop AI-driven literature curation.

Bioinformatics advances·2026
Same author

MR guided uncertainty quantification of tumour motion in open face masks versus closed face masks in head and neck radiotherapy.

Journal of medical imaging and radiation sciences·2026

Related Experiment Video

Updated: Sep 24, 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

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training

Edward G A Henderson1, Eliana M Vasquez Osorio1,2, Marcel van Herk1,2

  • 1The University of Manchester, Oxford Rd, Manchester M13 9PL, UK.

Physics and Imaging in Radiation Oncology
|May 6, 2022
PubMed
Summary

This study developed a 3D convolutional neural network (CNN) for accurate head and neck organ-at-risk auto-segmentation using limited data. The model achieved performance comparable to expert clinicians and state-of-the-art methods.

Keywords:
3D convolutional neural networkCT scan auto-segmentationLimited data

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

532

Related Experiment Videos

Last Updated: Sep 24, 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
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

532

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiotherapy Planning

Background:

  • Accurate segmentation of organs-at-risk (OARs) is vital for radiotherapy planning.
  • Training deep learning models like convolutional neural networks (CNNs) typically requires extensive datasets, which are often scarce for medical applications.
  • Automating OAR segmentation can improve efficiency and consistency in radiotherapy.

Purpose of the Study:

  • To develop a 3D CNN for accurate head and neck (HN) auto-segmentation of planning CT scans.
  • To investigate the feasibility of training a high-performing CNN with a small dataset (34 CTs).
  • To optimize CNN architecture elements for improved segmentation accuracy.

Main Methods:

  • Custom 3D CNN architecture with variations in input contrast channels, convolution types (resize vs. transpose), and loss functions (overlap metrics, cross-entropy).
  • Performance evaluation using 95th percentile Hausdorff distance and mean distance-to-agreement (mDTA).
  • Comparison against inter-observer variability of expert segmentations and validation on a public dataset against state-of-the-art (SOTA) methods.

Main Results:

  • The optimized CNN configuration demonstrated competitive performance with SOTA auto-segmentation methods on a public dataset.
  • Achieved specific mDTA values for key HN OARs, indicating high accuracy.
  • Segmentation accuracy was comparable to inter-clinician deviations.

Conclusions:

  • A 3D CNN can achieve accurate HN OAR auto-segmentation even with a small training dataset.
  • Careful tuning of CNN architecture and training parameters is crucial for optimizing performance.
  • The proposed method offers a viable solution for automated segmentation in radiotherapy planning, addressing data scarcity challenges.