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

BrainGAN Framework for Generating Synthetic Contrast-Enhanced Multisequence MRI in Brain Metastases.

Journal of imaging informatics in medicine·2026
Same author

Diagnostic Value of Ocular Hemodynamics and Choroidal Thickness in Unilateral Sudden Sensorineural Hearing Loss: Non-Invasive Biomarkers of Systemic Microvascular Disease.

Diagnostics (Basel, Switzerland)·2026
Same author

Alzheimer's and Parkinson's Detection with Video-Based Hybrid Deep Learning from Brain MRI.

Journal of imaging informatics in medicine·2026
Same author

Clinical and Quantitative Radiologic Evaluation of Cochlear Implant Candidates: Implications for Surgical Planning.

The Journal of craniofacial surgery·2026
Same author

Retrieval-augmented generation-enhanced large language models for comprehensive CAD-RADS 2.0 categorization from structured coronary CTA reports.

Radiologie (Heidelberg, Germany)·2026
Same author

Letter to the Editor: comments on the diagnostic value of ADC texture analysis in PI-RADS 5 lesions.

Diagnostic and interventional radiology (Ankara, Turkey)·2026

Related Experiment Video

Updated: Jul 28, 2025

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

1.9K

Deep Network-Based Comprehensive Parotid Gland Tumor Detection.

Kubilay Muhammed Sunnetci1, Esat Kaba2, Fatma Beyazal Celiker2

  • 1Osmaniye Korkut Ata University, Department of Electrical and Electronics Engineering, Osmaniye 80000, Turkey (K.M.S.); Kahramanmaraş Sütçü İmam University, Department of Electrical and Electronics Engineering, Kahramanmaraş 46050, Turkey (K.M.S., A.A.).

Academic Radiology
|June 4, 2023
PubMed
Summary

This study developed an AI model for automatic parotid gland tumor segmentation using deep learning on MR images. The system achieved high accuracy, offering a faster alternative to manual segmentation for clinical use.

Keywords:
Deep learningMagnetic resonance imagingParotid gland tumorSegmentation

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

2.8K
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

2.5K

Related Experiment Videos

Last Updated: Jul 28, 2025

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

1.9K
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

2.8K
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

2.5K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Salivary gland tumors are rare, accounting for 2%-6% of head and neck tumors, predominantly affecting the parotid gland.
  • Magnetic resonance (MR) imaging is crucial for diagnosing parotid gland tumors, assessing tumor characteristics, and planning treatment.
  • Manual segmentation of parotid gland tumors is time-consuming and requires specialized expertise.

Purpose of the Study:

  • To develop and evaluate deep learning-based automatic segmentation models for parotid gland tumors (PGT).
  • To create a user-friendly software application for PGT segmentation.
  • To compare the performance of different deep learning architectures for PGT segmentation on various MR image contrasts.

Main Methods:

  • A dataset of 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images was utilized.
  • Six deep learning models based on ResNet18 and Xception-based DeepLab v3+ were trained and evaluated.
  • Images were preprocessed, segmented manually by experts, and split into training (80%) and testing (20%) sets.

Main Results:

  • The ResNet18-based DeepLab v3+ architecture trained on T1C-w images achieved the highest accuracy (0.96153) and weighted Intersection over Union (0.92601).
  • The developed models demonstrated competitive performance compared to existing literature, with independent training for T1-w, T1C-w, and T2-w images.
  • The study successfully developed a software application for automatic PGT segmentation.

Conclusions:

  • The proposed deep learning approach offers an efficient and accurate method for automatic parotid gland tumor segmentation.
  • The developed software application can significantly reduce workload and costs associated with manual segmentation.
  • This study contributes a valuable tool to the literature, potentially improving the diagnosis and treatment planning of parotid gland tumors.