Jove
Visualize
Contact Us

Related Concept Videos

Goiter01:27

Goiter

32
Goiter refers to an abnormal enlargement of the thyroid gland that may appear as a diffuse goiter (uniform enlargement) or nodular (single or multiple nodules). Functionally, it is classified as nontoxic (normal/low hormone levels) or toxic (excess hormone production).PathophysiologyDiffuse thyroid enlargement typically results from prolonged stimulation by thyroid-stimulating hormone (TSH) or TSH-like agents, commonly seen in hypothyroidism or iodine deficiency. In contrast, in hyperthyroid...
32
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. Interobserver Agreement Between Artificial Intelligence Models In The Thyroid Imaging And Reporting Data System (tirads) Assessment Of Thyroid Nodules.
  1. Home
  3. Interobserver Agreement Between Artificial Intelligence Models In The Thyroid Imaging And Reporting Data System (tirads) Assessment Of Thyroid Nodules.

Related Experiment Video

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

465

Interobserver agreement between artificial intelligence models in the thyroid imaging and reporting data system

Andrea Leoncini1, Pierpaolo Trimboli2,3

  • 1Clinic for Radiology, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale (EOC), Bellinzona, Switzerland.

Endocrine
|May 15, 2025

View abstract on PubMed

Summary
This summary is machine-generated.
Keywords:
Artificial IntelligenceInter-observer agreementTIRADSThyroidUltrasound

More Related 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

1.7K
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

503

Related Experiment Videos

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

465
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
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

503

Artificial intelligence (AI) models show variable agreement when assessing thyroid nodule (TN) malignancy risk using different Thyroid Imaging and Reporting Data Systems (TIRADSs). This variability highlights the need for awareness among clinicians and patients regarding AI interpretations in thyroid nodule assessment.

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Radiology and Diagnostic Imaging
  • Oncology and Cancer Research

Background:

  • Ultrasound (US) is crucial for assessing thyroid nodule (TN) malignancy risk (RoM).
  • International Thyroid Imaging and Reporting Data Systems (TIRADSs) guide TN assessment.
  • The integration of artificial intelligence (AI) necessitates understanding AI's interpretation of TIRADSs and agreement in TN risk stratification.

Purpose of the Study:

  • To analyze interobserver agreement (IOA) among AI models in assessing TN RoM.
  • To compare AI performance across different TIRADSs categories (ACR-TIRADS, EU-TIRADS, K-TIRADS).
  • To evaluate AI interpretation of TIRADSs terminology and risk assessment consistency.

Main Methods:

  • Three AI models (ChatGPT, Google Gemini, Claude) were utilized.
  • AI assessments were performed using scenarios based on ACR-TIRADS, EU-TIRADS, and K-TIRADS.
  • Interobserver agreement was quantified using kappa (κ) values.

    • Main Results:

    • Kappa values for IOA varied significantly across AI models and TIRADSs.
    • With ACR-TIRADS, κ ranged from 0.53 to 0.90.
    • With EU-TIRADS, κ ranged from 0.62 to 0.73.
    • With K-TIRADS, κ ranged from 0.61 to 0.88.

    Conclusions:

    • Non-negligible variability exists in AI-driven TN risk assessment.
    • Clinicians and patients should be informed about AI interpretation variability.
    • Further research is needed to standardize AI application in thyroid nodule evaluation.