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

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data.

ArXiv·2026
Same author

Singular Value Decomposition-Based Coil Combination Improves the Accuracy and Noise-Robustness of Quantitative Susceptibility Maps.

medRxiv : the preprint server for health sciences·2026
Same author

Characterization of Gaming-Related Symptoms and Musculoskeletal Pain Complaints in Individuals Who Participate in Electronic Gaming.

American journal of lifestyle medicine·2026
Same author

Automatic multiple sclerosis lesion segmentation in the spinal cord using 3 T and 7 T MP2RAGE images.

Multiple sclerosis and related disorders·2026
Same author

Characteristics of training and lifestyle in high-level competitive golfers.

PM & R : the journal of injury, function, and rehabilitation·2026
Same author

Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same journal

Etomidate in Severe Cushing Syndrome: An Underutilized Bridge in Endocrine Emergency Care.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same journal

Insights from secular trend of major osteoporotic fractures in people with and without diabetes: 15-year population-based study (2009 - 2023).

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same journal

Early Metabolic Risk in Childhood Brain Cancer Survivors with Childhood-Onset Growth Hormone Deficiency.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same journal

The Use of Directed Ablative Techniques for Autonomously Functioning Thyroid Nodules: A Statement from the North American Society for Interventional Thyroidology.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same journal

North American Society for Interventional Thyroidology (NASIT) Statement on Directed Ablative Therapy for the Management of Cervical Recurrence of Papillary Thyroid Cancer.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same journal

Tirzepatide versus conventional GLP-1 receptor agonists for treatment simplification in type 2 diabetes mellitus: a real-world study.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
See all related articles

Related Experiment Video

Updated: Jun 17, 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

1.8K

Combining Image Similarity and Predictive Artificial Intelligence Models to Decrease Subjectivity in Thyroid Nodule

Govind Nair1, Aishwarya Vedula2, Ethan Thomas Johnson3

  • 1Saint Louis University Medical Scholars Program, Saint Louis University, Saint Louis, Missouri.

Endocrine Practice : Official Journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists
|August 10, 2024
PubMed
Summary
This summary is machine-generated.

This study shows an artificial intelligence (AI) tool effectively risk stratifies thyroid nodules, potentially reducing unnecessary fine needle aspirations. The AI demonstrated strong performance across datasets, correlating well with ACR TI-RADS scores.

Keywords:
AITI-RADSimage similarityminimally invasivepredictive AIthyroid cancerthyroid malignancythyroid nodule

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

566
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

1.8K

Related Experiment Videos

Last Updated: Jun 17, 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

1.8K
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

566
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

1.8K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Diagnostic accuracy of medical procedures

Background:

  • Thyroid nodules are common, requiring accurate risk stratification to determine the need for invasive procedures like fine needle aspiration (FNA).
  • Current risk stratification relies on imaging features and scoring systems, such as the American College of Radiology Thyroid Imaging and Data System (ACR TI-RADS).
  • Predictive artificial intelligence (AI) offers a potential tool to enhance the accuracy and efficiency of thyroid nodule risk assessment.

Purpose of the Study:

  • To evaluate the efficacy of a combined predictive artificial intelligence (AI) and image similarity model for risk stratifying thyroid nodules.
  • To assess the AI application's performance in predicting malignancy and correlating with the ACR TI-RADS scoring system.
  • To determine the potential impact of the AI tool on reducing the need for fine needle aspiration (FNA) in thyroid nodule diagnosis.

Main Methods:

  • A retrospective external validation study was conducted using two distinct datasets of thyroid nodule ultrasound images.
  • The datasets included 192 nodules from Stanford and 118 from a private practice, with definitive diagnoses confirmed by cytology or surgical pathology.
  • An AI application was employed to predict nodule diagnosis and assign an ACR TI-RADS score.

Main Results:

  • In the Stanford dataset, the AI achieved a sensitivity of 1.0, specificity of 0.55, PPV of 0.18, and NPV of 1.0 (AUC-ROC: 0.78).
  • In the private practice dataset, the AI demonstrated higher performance with sensitivity of 0.91, specificity of 0.95, PPV of 0.8, NPV of 0.98 (AUC-ROC: 0.93, Accuracy: 0.94).
  • The AI's ACR TI-RADS score showed strong polychoric correlations (0.67 in Stanford, 0.94 in private practice).

Conclusions:

  • The AI application exhibited robust sensitivity and negative predictive value across both datasets, indicating its reliability in ruling out malignancy.
  • The AI tool showed potential to reduce fine needle aspiration (FNA) by 61.5% and correlated strongly with ACR TI-RADS, suggesting improved diagnostic efficiency.
  • Variability in positive predictive value highlights the need for consistent image selection and consideration of malignancy prevalence in diverse clinical settings for widespread implementation.