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

Gold nanoparticle and carbon dot coated SnO2 nanocomposite with high photo-electronic catalytic activity for oxygen evolution reaction.

Dalton transactions (Cambridge, England : 2003)·2015
Same author

Biased signaling in naturally occurring mutations in human melanocortin-3 receptor gene.

International journal of biological sciences·2015
Same author

Improved Biofilm Antimicrobial Activity of Polyethylene Glycol Conjugated Tobramycin Compared to Tobramycin in Pseudomonas aeruginosa Biofilms.

Molecular pharmaceutics·2015
Same author

Preconditioning of model biocarriers by soluble pollutants: a QCM-D study.

ACS applied materials & interfaces·2015
Same author

Influence of mother-daughter attachment on substance use: a longitudinal study of a Latina community-based sample.

Journal of studies on alcohol and drugs·2015
Same author

STAT4 rs7574865 G/T and PTPN22 rs2488457 G/C polymorphisms influence the risk of developing juvenile idiopathic arthritis in Han Chinese patients.

PloS one·2015

Related Experiment Video

Updated: May 29, 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

2.6K

Automatic cervical lymph nodes detection and segmentation in heterogeneous computed tomography images using deep

Wenjun Liao1, Xiangde Luo2, Lu Li1

  • 1Department of Radiation Oncology, Sichuan Cancer Hospital and Institute, Sichuan Cancer Center, Cancer Hospital Affiliate to School of Medicine, University of Electronic Science and Technology of China, Chengdu, 610041, China.

Scientific Reports
|February 5, 2025
PubMed
Summary

A deep learning model was developed for automatic detection and segmentation of neck lymph nodes in CT scans. This AI tool shows promise in assisting oncologists by accurately identifying and outlining lymph nodes, potentially reducing manual workload.

Keywords:
Deep learningDetectionHead and neck cancerNeck lymph nodeSegmentation

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

8.5K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Related Experiment Videos

Last Updated: May 29, 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

2.6K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.5K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Accurate detection and segmentation of neck lymph nodes (LNs) are crucial for head and neck cancer staging and treatment planning.
  • Manual segmentation of LNs in computed tomography (CT) images is time-consuming and subject to inter-observer variability.

Purpose of the Study:

  • To develop and validate a deep learning model for automatic detection and segmentation of neck LNs in CT images using transfer learning.
  • To assess the model's performance on both internal and external validation cohorts.

Main Methods:

  • Utilized the nnUNet deep learning model, pre-trained on a large head and neck dataset and fine-tuned for LN detection and segmentation.
  • Trained and validated the model using a dataset of 11,013 annotated LNs from 626 head and neck cancer patients across four hospitals.
  • Evaluated detection using sensitivity, positive predictive value (PPV), and false positive rate per volume (FP/vol); segmentation assessed via Dice Similarity Coefficient (DSC) and Hausdorff distance 95th percentile (HD95).

Main Results:

  • The model achieved a sensitivity of 54.6% and PPV of 69.0% with 3.4 FP/vol on the internal test cohort.
  • External validation showed sensitivity ranging from 45.7% to 63.5% across different cohorts.
  • Segmentation performance demonstrated a mean DSC of 0.72-0.74 and mean HD95 of 2.73-3.78 mm, comparable to experienced oncologists.

Conclusions:

  • The developed deep learning model shows significant potential for automated neck LN detection and segmentation in CT images.
  • The model's performance is robust across different datasets and comparable to human experts.
  • This AI tool could streamline the workflow for oncologists, reducing the burden of manual segmentation during adaptive radiotherapy.