Jove
Visualize
Contact Us

Related Concept Videos

Ultrasonography01:17

Ultrasonography

4.5K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
4.5K
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
  1. Home
  3. Differentiation Of Benign And Malignant Parotid Gland Tumors Based On The Fusion Of Radiomics And Deep Learning Features On Ultrasound Images.
  1. Home
  3. Differentiation Of Benign And Malignant Parotid Gland Tumors Based On The Fusion Of Radiomics And Deep Learning Features On Ultrasound Images.

Related Experiment Video

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

1.8K

Differentiation of benign and malignant parotid gland tumors based on the fusion of radiomics and deep learning

Yi Wang1, Jiening Gao1, Zhaolin Yin1

  • 1Department of Ultrasound, The Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei, China.

Frontiers in Oncology
|May 28, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

This study developed a deep learning radiomics nomogram (DLRN) using ultrasound images to accurately differentiate benign and malignant parotid gland tumors. The DLRN model significantly improved diagnostic performance, aiding in personalized treatment strategies.

Keywords:
deep learningfeature fusionnomogramparotid gland tumorsradiomicsultrasound

More Related Videos

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

587
Author Spotlight: A Focus on Standardized Salivary Gland Ultrasound Protocol in Connective Tissue Disease Research
07:25

Author Spotlight: A Focus on Standardized Salivary Gland Ultrasound Protocol in Connective Tissue Disease Research

Published on: October 13, 2023

2.2K

Related Experiment Videos

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

1.8K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

587
Author Spotlight: A Focus on Standardized Salivary Gland Ultrasound Protocol in Connective Tissue Disease Research
07:25

Author Spotlight: A Focus on Standardized Salivary Gland Ultrasound Protocol in Connective Tissue Disease Research

Published on: October 13, 2023

2.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Parotid gland tumors present complex pathological classifications and imaging manifestations.
  • Accurate preoperative identification is critical for clinical management and prognosis.
  • Distinguishing benign parotid gland tumors (BPGTs) from malignant parotid gland tumors (MPGTs) remains challenging.

Purpose of the Study:

  • To construct and compare the performance of various models for differentiating BPGTs and MPGTs using ultrasound (US) images.
  • To evaluate clinical models, traditional radiomics, deep learning (DL), and deep learning radiomics (DLR) models.
  • To develop an optimal DLR model integrated with clinical and US features for improved diagnostic accuracy.

Main Methods:

  • Retrospective analysis of 526 patients with confirmed parotid gland tumors.
  • Development of traditional radiomics and DL models (DenseNet121, VGG19, ResNet50) using handcrafted radiomics (HCR) and DL features.
  • Construction of predictive models using seven machine learning classifiers and development of a DLR nomogram (DLRN) integrating clinical and US features.
  • Performance assessment using Receiver Operating Characteristic (ROC) curves and clinical utility evaluation via Decision Curve Analysis (DCA).

    • Main Results:

    • The DLR model based on ExtraTrees achieved high AUC values (0.943 training, 0.916 testing).
    • The DLRN model further enhanced performance with AUC values of 0.960 (training) and 0.934 (testing).
    • DCA indicated superior clinical benefits of the DLRN model compared to other models.

    Conclusions:

    • The DLRN model based on US images demonstrates exceptional performance in distinguishing BPGTs and MPGTs.
    • This approach provides reliable information for personalized diagnosis and treatment planning.
    • The findings support the clinical utility of DLRN in managing parotid gland tumors.