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

Synthesis and Regulation of Thyroid Hormones01:20

Synthesis and Regulation of Thyroid Hormones

7.0K
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...
7.0K
The Thyroid Gland01:23

The Thyroid Gland

6.8K
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...
6.8K
Hyperthyroidism II: Pathophysiology01:27

Hyperthyroidism II: Pathophysiology

10
Hyperthyroidism is a hypermetabolic state caused by elevated levels of thyroid hormones, triiodothyronine (T3) and thyroxine (T4). It results from dysregulation at the thyroid, pituitary, or immune system level and affects multiple organ systems.PathophysiologyThe most common cause of hyperthyroidism is Graves’ disease, an autoimmune disorder in which antibodies, specifically thyroid-stimulating antibodies (TSAb), a subtype of TSH receptor antibodies (TRAb), bind to and activate TSH...
10
Hyperthyroidism I: Introduction01:25

Hyperthyroidism I: Introduction

11
Hyperthyroidism is a type of thyrotoxicosis characterized by the thyroid gland's overproduction of the thyroid hormones triiodothyronine (T3) and thyroxine (T4). This hormone excess increases the basal metabolic rate and enhances sensitivity to catecholamines.DiagnosisDiagnosis is based on clinical features and biochemical testing. It typically shows suppressed thyroid-stimulating hormone (TSH) levels below 0.4 mIU/L, with elevated free T3 and/or T4. Additional tests, including thyroid...
11
Goiter01:27

Goiter

21
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...
21

You might also read

Related Articles

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

Sort by
Same author

Correction: ThyroFusion: A Multi-modal Deep Learning Framework Integrating Vision and Language for Thyroid Nodule Malignancy Risk Assessment.

Journal of imaging informatics in medicine·2026
Same author

Propagation Characteristics of Multi-Frequency Arc-Shaped Flat-Plate Ultrasound in Xanthan Gum Viscous Systems and Its Influence on Rheological Properties.

Foods (Basel, Switzerland)·2025
Same author

NEPE Propellant Mesoscopic Modeling and Damage Mechanism Study Based on Inversion Algorithm.

Materials (Basel, Switzerland)·2024
Same author

A multifunctional polymeric additive with a synergistic effect for high-performance lithium-ion batteries.

Chemical communications (Cambridge, England)·2023
Same author

A Brush-like Li-Ion Exchange Polymer as Potential Artificial Solid Electrolyte Interphase for Dendrite-Free Lithium Metal Batteries.

The journal of physical chemistry letters·2022
Same author

Imidazolium-Type Poly(ionic liquid) Endows the Composite Polymer Electrolyte Membrane with Excellent Interface Compatibility for All-Solid-State Lithium Metal Batteries.

ACS applied materials & interfaces·2022

Related Experiment Video

Updated: Apr 24, 2026

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

2.6K

ThyroFusion: A Multi-modal Deep Learning Framework Integrating Vision and Language for Thyroid Nodule Malignancy Risk

Tianhao Xiang1, Zhenyuan Hu2

  • 1School of Electronics and Information, Xian Polytechnic University, Xian, 710048, China. tianhao@stu.xpu.edu.cn.

Journal of Imaging Informatics in Medicine
|April 22, 2026
PubMed
Summary
This summary is machine-generated.

ThyroFusion, a novel multi-modal deep learning framework, significantly improves thyroid nodule malignancy risk assessment by integrating ultrasound images and clinical reports. This advanced AI tool outperforms current methods and aids radiologists in diagnosis.

Keywords:
Computer-aided diagnosisCross-modal attentionMulti-modal deep learningThyroFusionThyroid 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

1.3K
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

1.2K

Related Experiment Videos

Last Updated: Apr 24, 2026

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

2.6K
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

1.3K
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

1.2K

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Imaging Analysis
  • Deep Learning for Diagnostics

Background:

  • Distinguishing benign from malignant thyroid nodules is clinically challenging.
  • Current deep learning models often rely on single data sources, limiting diagnostic accuracy.
  • Multi-modal data integration offers potential for improved thyroid nodule assessment.

Purpose of the Study:

  • To develop and validate ThyroFusion, a multi-modal deep learning framework for enhanced thyroid nodule malignancy risk assessment.
  • To integrate ultrasound images, segmentation masks, and clinical text reports for comprehensive analysis.
  • To compare ThyroFusion's performance against single-modal deep learning models and human radiologists.

Main Methods:

  • Developed ThyroFusion, a multi-modal fusion framework using a dual-stream ResNet-50 encoder, Set Transformer, and bidirectional cross-modal attention.
  • Integrated visual features from ultrasound images/masks and textual features from reports (BioBERT).
  • Trained on 1472 cases and validated on 4530 external cases across multiple centers and public datasets (DDTI, TN3K).

Main Results:

  • ThyroFusion achieved high AUCs: 0.937 (internal) and 0.896 (external validation).
  • Significantly outperformed single-modal models (e.g., ResNet-50, DenseNet-121, EfficientNet-B4, Vision Transformer) on external validation (all p < 0.001).
  • Outperformed senior radiologists (AUC 0.809) and improved junior radiologists' performance as an assistive tool (ΔAUC = 0.126).
  • Demonstrated robust cross-domain generalization on public datasets (DDTI AUC 0.893, TN3K AUC 0.881).

Conclusions:

  • ThyroFusion demonstrates robust and superior performance in thyroid nodule malignancy risk assessment.
  • Multi-modal data integration via bidirectional cross-modal attention enhances diagnostic capabilities.
  • The framework serves as a promising clinical decision support tool, improving diagnostic accuracy beyond current methods and human expertise.