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

The Thyroid Gland01:23

The Thyroid Gland

4.2K
The thyroid gland is a small, butterfly-shaped gland located in the neck and covers the anterior surface of the trachea. The gland has two lateral lobes connected by a thin tissue mass called the isthmus. Internally, each lobe comprises many small spherical structures known as thyroid follicles, surrounded by a network of blood vessels.
The follicles have a central cavity lined by simple cuboidal to squamous epithelial cells called follicular cells. These cells produce the glycoprotein...
4.2K
Synthesis and Regulation of Thyroid Hormones01:20

Synthesis and Regulation of Thyroid Hormones

4.9K
Low blood levels of the thyroid hormones — triiodothyronine (T3) and thyroxine (T4) — signal the hypothalamus to release the thyrotropin-releasing hormone (TRH). TRH then reaches the pituitary gland and stimulates the release of thyroid-stimulating hormone(TSH) into the bloodstream.
Upon reaching the thyroid gland, TSH stimulates the follicular cells' active uptake of iodide ions from the blood. The ions diffuse to the apical surface of the cells and are oxidized to iodine. The...
4.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hierarchical dynamic model for risk-stratified screening of nasopharyngeal carcinoma.

Nature communications·2026
Same author

Deep Learning Model Based on Tumor and Visceral Adipose Tissue CT Features for Predicting Peritoneal Metastasis Risk after Radical Gastrectomy in Serosa-Invasive Gastric Cancer.

Radiology. Imaging cancer·2026
Same author

Error Detection in Emergency Radiology Reports Using a Large Language Model: Multistage Evaluation Study.

Journal of medical Internet research·2026
Same author

Evaluation of the ultrasonic arterial measurement and analysis system for predicting 10-year atherosclerotic cardiovascular disease risk in patients with type 2 diabetes.

Quantitative imaging in medicine and surgery·2025
Same author

Radiomic Model Associated with Tumor Microenvironment Predicts Immunotherapy Response and Prognosis in Patients with Locoregionally Advanced Nasopharyngeal Carcinoma.

Research (Washington, D.C.)·2025
Same author

Artificial Intelligence Can Predict Personalized Immunotherapy Outcomes in Cancer.

Cancer immunology research·2025

Related Experiment Video

Updated: Aug 29, 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

Thy-Wise: An interpretable machine learning model for the evaluation of thyroid nodules.

Zhe Jin1, Shufang Pei2, Lizhu Ouyang3

  • 1Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China.

International Journal of Cancer
|September 12, 2022
PubMed
Summary
This summary is machine-generated.

Machine learning models for thyroid nodules improve diagnostic accuracy and reduce unnecessary biopsies compared to current systems. An interpretable AI model, Thy-Wise, enhances clinical decision-making for thyroid nodule diagnosis.

Keywords:
diagnosismachine learningrandom forestthyroid nodulesultrasonography

More Related Videos

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.0K
A Personalized 3D-Printed Model for Preoperative Evaluation in Thyroid Surgery
04:42

A Personalized 3D-Printed Model for Preoperative Evaluation in Thyroid Surgery

Published on: February 17, 2023

1.4K

Related Experiment Videos

Last Updated: Aug 29, 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
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.0K
A Personalized 3D-Printed Model for Preoperative Evaluation in Thyroid Surgery
04:42

A Personalized 3D-Printed Model for Preoperative Evaluation in Thyroid Surgery

Published on: February 17, 2023

1.4K

Area of Science:

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

Background:

  • Current thyroid nodule risk stratification systems exhibit low specificity, leading to high rates of unnecessary biopsies.
  • Machine learning (ML) offers potential for improved thyroid nodule diagnosis but often lacks interpretability.
  • The American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS) is a widely used standard for risk stratification.

Purpose of the Study:

  • To develop and validate interpretable machine learning models for thyroid nodule diagnosis.
  • To compare the performance of ML models against the established ACR TI-RADS system.
  • To assess the impact of ML models on diagnostic accuracy and unnecessary biopsy rates.

Main Methods:

  • Developed and validated machine learning models (Random Forest, SVM, XGBoost) using ultrasonography (US) data and clinical characteristics from 3965 thyroid nodules.
  • Utilized a SHapley Additive exPlanation (SHAP) algorithm to interpret the best-performing ML model, named Thy-Wise.
  • Compared diagnostic performance (accuracy, sensitivity, specificity) and unnecessary biopsy rates of ML models and ACR TI-RADS.

Main Results:

  • The US-only Random Forest model (Thy-Wise) demonstrated superior performance.
  • Thy-Wise achieved higher accuracy (82.4% internal, 82.1% external) and specificity (78.7% internal, 78.5% external) compared to ACR TI-RADS.
  • Thy-Wise significantly reduced unnecessary biopsies (15.3% internal, 15.7% external) while maintaining high sensitivity (91.7% internal, 91.9% external).

Conclusions:

  • Interpretable machine learning models, like Thy-Wise, offer improved diagnostic accuracy and efficiency for thyroid nodules over traditional methods.
  • The SHAP-based interpretability of Thy-Wise facilitates clinical understanding and adoption.
  • This approach holds promise for reducing invasive procedures and optimizing patient management in thyroid nodule diagnosis.