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

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

Current State and Future of Systemic Treatment for Elderly Patients With Head and Neck Cancer Undergoing Radiotherapy.

Head & neck·2026
Same author

Optimal radiotherapy dose scheduling with variable fraction sizes and breaks via sequential mixed-integer convex programming.

Physics and imaging in radiation oncology·2026
Same author

Adaptive and sequential cancer therapies emerge from treatment schedule optimization.

Research square·2026
Same author

Metastatic Trajectories in Non-Small Cell Lung Cancer Guide Local and Systemic Therapies.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026
Same author

Curvature on Graphs with Negative Edge Weights.

IEEE transactions on network science and engineering·2026

Related Experiment Video

Updated: Oct 11, 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

Prospectively-validated deep learning model for segmenting swallowing and chewing structures in CT.

Aditi Iyer1, Maria Thor1, Ifeanyirochukwu Onochie2

  • 1Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, United States of America.

Physics in Medicine and Biology
|December 7, 2021
PubMed
Summary
This summary is machine-generated.

This study developed deep learning models to automatically segment head and neck structures for radiotherapy planning, significantly reducing manual effort and improving efficiency for cancer treatment.

Keywords:
auto-segmentationdeep learningdysphagiaradiation therapyswallowing and chewing structurestrismus

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K

Related Experiment Videos

Last Updated: Oct 11, 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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiation Oncology

Background:

  • Accurate segmentation of swallowing and chewing structures is crucial for radiotherapy planning to minimize side effects like dysphagia and trismus.
  • Current manual segmentation is time-consuming and prone to inter-observer variability.

Purpose of the Study:

  • To develop and validate an automated segmentation method for key head and neck structures involved in swallowing and chewing.
  • To improve the efficiency and accuracy of radiotherapy treatment planning.

Main Methods:

  • Deep learning models (DeepLabV3+) were trained on CT scans from 242 head and neck cancer patients.
  • A cascaded framework and model ensembling were used to enhance segmentation accuracy across different views.
  • Prospective evaluation assessed the manual editing required for clinical use on 91 additional scans.

Main Results:

  • The models achieved high Dice Similarity Coefficients (DSC): 0.87 for masseters, 0.80 for medial pterygoids, 0.81 for larynx, and 0.69 for pharyngeal constrictors.
  • Auto-segmentations demonstrated better agreement with individual observers than inter-observer agreement.
  • Prospective analysis indicated minor manual modifications were needed, suggesting increased clinical efficiency.

Conclusions:

  • Deep learning-based auto-segmentation models for swallowing and chewing structures in CT are effective for radiotherapy planning.
  • This is the first prospectively validated deep learning model for segmenting these structures in CT.
  • Open-source models are available to promote research and reproducibility.