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

Engineering Coumarin-Based Afterglow Luminescence Probes for Activatable Imaging Peroxynitrite In Vivo.

Angewandte Chemie (International ed. in English)·2026
Same author

2024 International expert consensus on ultrasound-guided thermal ablation for secondary and tertiary hyperparathyroidism.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2026
Same author

A "calcification"-enhanced deep learning approach for precise differentiation of thyroid nodules.

Cancer imaging : the official publication of the International Cancer Imaging Society·2025
Same author

Early prediction of thyroid capsule invasion in papillary microcarcinoma using ultrasound-based deep learning models: a retrospective multicenter study.

Insights into imaging·2025
Same author

Reply to the Letter to the Editor: Synthesize contrast-enhanced ultrasound image of thyroid nodules via generative adversarial networks.

European radiology·2025
Same author

Synthesize contrast-enhanced ultrasound image of thyroid nodules via generative adversarial networks.

European radiology·2025

Related Experiment Video

Updated: Jul 10, 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 learning approaches for differentiating thyroid nodules with calcification: a two-center study.

Chen Chen1,2,3, Yuanzhen Liu1,2,3, Jincao Yao1,4,5

  • 1Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, China.

BMC Cancer
|November 23, 2023
PubMed
Summary

Deep learning models significantly outperform radiologists in identifying malignant thyroid calcified nodules. These artificial intelligence tools can also improve diagnostic accuracy when used by clinicians.

Keywords:
CalcificationDeep learningThyroid noduleUltrasonography

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

639
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

1.9K

Related Experiment Videos

Last Updated: Jul 10, 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: 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

639
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

1.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Thyroid nodules frequently exhibit calcification, but its diagnostic significance is not fully understood.
  • Distinguishing benign from malignant calcified thyroid nodules requires objective assessment methods.

Purpose of the Study:

  • To develop and evaluate deep learning (DL) models for objective differentiation of benign and malignant thyroid calcified nodules.
  • To compare the diagnostic performance of DL models against that of experienced radiologists.

Main Methods:

  • Retrospective analysis of 631 pathologically confirmed thyroid nodules from two centers.
  • Utilized ultrasound image datasets for deep learning model training and validation.
  • Evaluated diagnostic performance using the area under the receiver-operator characteristic curve (AUROC).

Main Results:

  • The Xception DL model achieved the highest AUROC (0.970), followed by DenseNet169 (0.959).
  • Both DL models demonstrated superior diagnostic performance compared to radiologists (P < 0.05).
  • Xception's effectiveness is linked to its use of deep separable convolution for efficient feature extraction.

Conclusions:

  • Deep learning models significantly outperform radiologists in classifying calcified thyroid nodules.
  • DL-based tools have the potential to enhance radiologists' diagnostic capabilities for thyroid nodules.