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

Stop LCNP: High dose corticosteroid therapy for late radiation-associated lower cranial neuropathy: A report of the phase I dose finding trial and parallel prospective data registry.

medRxiv : the preprint server for health sciences·2026
Same author

LLM-Driven Extraction of NI-RADS and Imaging Tumor Characteristics to Enhance Oropharyngeal Cancer Survivorship Surveillance.

medRxiv : the preprint server for health sciences·2026
Same author

Targeted autonomic testing for radiation‑induced baroreflex failure in head and neck cancer survivors: index case and early program experience.

Cardio-oncology (London, England)·2026
Same author

Feasibility of longitudinal relaxation rate mapping with non-Cartesian sampling and compressed sensing on a 1.5 T magnetic resonance linear accelerator.

Physics and imaging in radiation oncology·2026
Same author

MRIgRT real-time target tracking: TrackRAD2025 challenge report.

Medical image analysis·2026
Same author

An evaluation of uncertainty quantification methods and measures for deep learning outcome prediction models in head and neck cancer radiotherapy.

Physics and imaging in radiation oncology·2026

Related Experiment Video

Updated: Jun 16, 2025

Modeling Oral-Esophageal Squamous Cell Carcinoma in 3D Organoids
10:43

Modeling Oral-Esophageal Squamous Cell Carcinoma in 3D Organoids

Published on: December 23, 2022

3.3K

Three-Dimensional Deep Learning Normal Tissue Complication Probability Model to Predict Late Xerostomia in Patients

Hung Chu1, Suzanne P M de Vette1, Hendrike Neh1

  • 1Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.

International Journal of Radiation Oncology, Biology, Physics
|August 15, 2024
PubMed
Summary
This summary is machine-generated.

Deep learning models show promise in predicting xerostomia after head and neck cancer radiation therapy. Transfer learning improved external validation, highlighting the need for multicenter data to generalize these normal tissue complication probability (NTCP) models.

More Related Videos

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

499
Therapy Testing in a Spheroid-based 3D Cell Culture Model for Head and Neck Squamous Cell Carcinoma
06:11

Therapy Testing in a Spheroid-based 3D Cell Culture Model for Head and Neck Squamous Cell Carcinoma

Published on: April 20, 2018

9.8K

Related Experiment Videos

Last Updated: Jun 16, 2025

Modeling Oral-Esophageal Squamous Cell Carcinoma in 3D Organoids
10:43

Modeling Oral-Esophageal Squamous Cell Carcinoma in 3D Organoids

Published on: December 23, 2022

3.3K
Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

499
Therapy Testing in a Spheroid-based 3D Cell Culture Model for Head and Neck Squamous Cell Carcinoma
06:11

Therapy Testing in a Spheroid-based 3D Cell Culture Model for Head and Neck Squamous Cell Carcinoma

Published on: April 20, 2018

9.8K

Area of Science:

  • Radiation oncology
  • Medical imaging
  • Machine learning

Background:

  • Conventional normal tissue complication probability (NTCP) models for xerostomia in head and neck cancer patients rely on single-value variables like baseline xerostomia and mean salivary gland doses.
  • Predicting radiation-induced xerostomia accurately is crucial for improving patient quality of life post-treatment.

Purpose of the Study:

  • To enhance the prediction of late xerostomia using deep learning (DL) by incorporating 3-dimensional (3D) information from radiation dose distributions, CT imaging, and organ-at-risk segmentations.
  • To compare the performance of DL-based NTCP models against conventional models using clinical and dosimetric variables.

Main Methods:

  • An international cohort of 1208 head and neck cancer patients was used to train and validate DL models (CNN, EfficientNet-v2, ResNet).
  • Inputs included 3D dose distribution, CT scans, organ-at-risk segmentations, baseline xerostomia score, sex, and age.
  • DL model predictions were compared to a reference NTCP model using area under the receiver operating characteristic curve (AUC). Attention maps were used for visualization, and transfer learning was applied for external validation.

Main Results:

  • DL-based NTCP models achieved superior performance (AUCtest, 0.78-0.79) compared to the reference model (AUCtest, 0.74) on the independent test set.
  • Attention maps indicated DL models focused on major salivary glands, particularly the parotid glands.
  • Initial external validation showed lower DL model performance (AUCexternal, 0.63) than the reference model (AUCexternal, 0.66), but transfer learning improved DL performance (AUCtl, external, 0.66).

Conclusions:

  • DL-based NTCP models demonstrated better performance than the reference model when validated internally.
  • Transfer learning enhanced DL model performance on external data, suggesting its utility for improving generalizability.
  • Multicenter training data is essential for developing robust and generalizable DL-based NTCP models for radiation-induced xerostomia.