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: Feb 28, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.8K

Deep learning-based head and neck deformable image registration using spatio-temporal analysis and self attention.

Donghoon Lee1, Yu-Chi Hu1, Teeradon TreeChairusame2,3

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

Physics and Imaging in Radiation Oncology
|February 27, 2026
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

Limited Contribution of T<sub>1</sub> Relaxation to GluCEST MRI Signal Differences Across Four Rat Models with Distinct Pathophysiological Features.

Molecular imaging and biology·2026
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

Time-resolved GluCEST MRI of acute glutamate-related signal changes following kainic acid administration.

Journal of the neurological sciences·2026
Same author

SECmeres outperform extracellular vesicles as potential blood RNA biomarkers for Alzheimer's disease.

Nature communications·2026
Same author

Spatially Decoupled Sulfur Redox and Li<sup>+</sup> Transport in Polymer Electrolytes for Solid-State Li-S Batteries.

Nano letters·2026
This summary is machine-generated.

A new deep learning algorithm provides fast and accurate deformable image registration for head and neck cancer radiotherapy, enabling real-time adaptive treatment planning.

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Anatomical changes during head and neck cancer (HNC) radiotherapy necessitate adaptive strategies for accurate dose delivery.
  • Conventional deformable image registration (DIR) methods are too slow for online adaptive radiotherapy (ART) workflows.
  • Longitudinal imaging in HNC presents challenges for precise treatment adaptation.

Purpose of the Study:

  • To develop and evaluate a novel deep learning-based DIR algorithm for longitudinal HNC imaging.
  • To enable rapid and accurate image registration for real-time ART.
  • To improve dose delivery accuracy in HNC radiotherapy through advanced image registration.

Main Methods:

  • A patch-based deep learning model integrating 3D CNNs, self-attention, and ConvLSTM was developed.
Keywords:
AdaptiveradiotherapyDeep learningDeformable image registrationHead and neck cancer

More Related Videos

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

3.6K

Related Experiment Videos

Last Updated: Feb 28, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.8K
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

3.6K
  • The model predicted bidirectional deformation vector fields using a composite loss function.
  • Sixty HNC patient datasets (pCT and weekly CBCTs) were used for training and testing, benchmarking against LDDMM.

    • Main Results:

    • The deep learning DIR achieved bidirectional registration in under 3 minutes (average 30 seconds per patient), significantly faster than LDDMM.
    • The algorithm matched or exceeded LDDMM's accuracy, with Dice Similarity Coefficients above 0.8 for key structures.
    • Improved DVF consistency and reduced Hausdorff distances were observed, with no manual parameter tuning required.

    Conclusions:

    • The proposed DIR algorithm facilitates rapid, accurate, and consistent image registration for HNC.
    • This supports real-time adaptive radiotherapy workflows and retrospective dose accumulation.
    • The method offers a viable solution for personalized radiotherapy in HNC.