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

Beyond auto-segmentation: the case for planning and dosimetry AI in head and neck radiation oncology.

BMJ oncology·2026
Same author

Early Salivary Gland Shrinkage Is Associated With an Increased Risk of Acute Xerostomia in Head and Neck Cancer Radiation Therapy.

Advances in radiation oncology·2026
Same author

LEARNABLE HIERARCHICAL VISUAL CONTEXTS FOR TUMOR SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGES.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation.

Transactions on machine learning research·2026
Same author

MHub.ai: A Standardized Platform for Reproducible AI Research in Medical Imaging.

Research square·2026
Same author

DUAL CROSS-ATTENTION SIAMESE TRANSFORMER FOR RECTAL TUMOR REGROWTH ASSESSMENT IN WATCH-AND-WAIT ENDOSCOPY.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Related Experiment Video

Updated: Jan 6, 2026

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

3.3K

Dynamic multiatlas selection-based consensus segmentation of head and neck structures from CT images.

Rabia Haq1, Sean L Berry1, Joseph O Deasy1

  • 1Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, NY, 10065, USA.

Medical Physics
|October 7, 2019
PubMed
Summary

A new dynamic multiatlas approach improves head and neck organ-at-risk segmentation for radiation therapy. Structure weighted voting (SWV) achieved superior accuracy and reproducibility compared to other methods.

Keywords:
atlas segmentationcomputed tomography imageshead and neck

More Related Videos

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

Related Experiment Videos

Last Updated: Jan 6, 2026

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

3.3K
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

Area of Science:

  • Medical Physics
  • Radiotherapy
  • Medical Image Analysis

Background:

  • Manual delineation of head and neck (H&N) organs-at-risk (OARs) for radiation therapy planning is labor-intensive and prone to variability.
  • Automated segmentation methods are needed to improve efficiency and consistency in H&N radiotherapy.
  • Multi-atlas based segmentation (MABS) offers a promising avenue for automated OAR segmentation.

Purpose of the Study:

  • To develop and evaluate a dynamic multiatlas selection-based approach for fast and reproducible segmentation of H&N OARs.
  • To compare the performance of the proposed methods against traditional single best atlas and majority voting techniques.

Main Methods:

  • A dynamic multiatlas selection approach was developed, utilizing global weighted voting (GWV) and structure weighted voting (SWV) based on atlas alignment weights.
  • Atlases were selected based on an 'dynamic atlas attention index', with weights computed using CT-radiodensity and neighborhood descriptors.
  • Performance was evaluated on 77 H&N CT images using Dice similarity coefficient (DSC), Hausdorff distance (HD), and other metrics against expert delineations.

Main Results:

  • Both SWV and GWV methods significantly outperformed single best atlas (BA) and majority voting (MV) methods in segmentation accuracy (P < 0.001).
  • SWV yielded the highest segmentation accuracy across various OARs, with DSC values ranging from 0.60 to 0.88.
  • SWV demonstrated superior accuracy over GWV for submandibular glands (DSC = 0.60 vs 0.52, P = 0.019).

Conclusions:

  • The developed SWV and GWV methods provide more accurate automated segmentations for H&N OARs compared to existing multiatlas techniques.
  • The consensus maps generated can aid manual review by visualizing voxel-wise agreement between atlases.
  • This dynamic multiatlas approach enhances speed and reproducibility in radiotherapy planning.