Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Poor Knowledge and Suboptimal Practice Regarding Postmenopausal Osteoporosis Prevention Among Chinese Postmenopausal Women: A Structural Equation Model Analysis.

Journal of multidisciplinary healthcare·2026

Same author

Plasma exosome-derived miRNA-887-5p alleviates high glucose- and lipid-induced endothelial cell dysfunction.

Nutrition & diabetes·2026

Same author

Multimodal multitask deep learning for grading management system in non-small cell lung cancer.

Nature communications·2026

Same author

CLINT1 is a subtype-specific biomarker and a downstream effector of p53-R273H in lung adenocarcinoma migration.

Acta biochimica et biophysica Sinica·2026

Same author

Anlotinib for Advanced Peritoneal Follicular Dendritic Cell Sarcoma: A Case Report and Literature Revie.

Current cancer drug targets·2026

Same author

TMEM72 Inhibits the proliferation by promoting cellular senescence through the activation of the P38/MAPK signaling pathway in renal cell carcinoma.

Translational oncology·2026

Search research articles

Related Experiment Video

Updated: Jun 16, 2025

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Thyroid Cancer Central Lymph Node Metastasis Risk Stratification Based on Homogeneous Positioning Deep Learning.

Siqiong Yao^1,2, Pengcheng Shen¹, Fang Dai¹

¹State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China.

Research (Washington, D.C.)

|August 21, 2024

Summary

A new AI model, ACE-Net, accurately predicts central lymph node metastasis in thyroid cancer using ultrasound images. This tool aids clinical decisions, reducing unnecessary surgeries by 37.9% without missing positive cases.

More Related Videos

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

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

Published on: June 9, 2023

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Jun 16, 2025

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

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

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

Published on: June 9, 2023

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Area of Science:

Oncology
Medical Imaging
Artificial Intelligence

Background:

Assessing central lymph node metastasis (CLNM) risk in thyroid cancer is challenging due to a lack of definitive diagnostic criteria.
Nodule localization predicts CLNM, but quantifying this relationship is difficult with current measurement variability.

Purpose of the Study:

To develop an AI-driven method for accurate CLNM risk assessment in ultrasound-diagnosed thyroid cancer.
To quantify the relationship between nodule characteristics and CLNM to guide prophylactic lymph node surgery decisions.

Main Methods:

Developed ACE-Net, a model using differential isomorphism and graph transformers to extract nodule localization and morphology from 88,796 ultrasound images.
Employed interpretable methodology to identify CLNM predictors and generated a risk heatmap for visual representation.
Validated ACE-Net across 6 external multicenter tests.

Main Results:

ACE-Net achieved an AUC of 0.826, outperforming human expert accuracy (0.561) in predicting CLNM.
Identified high-risk CLNM areas via a risk heatmap, potentially linked to lymphatic pathways.
Determined metastasis likelihood exceeded 80% when nodal margin's minimum distance from the thyroid capsule was <1.25 mm.

Conclusions:

ACE-Net provides accurate CLNM prediction and interpretable insights for thyroid cancer management.
The model can reduce unnecessary lymph node dissections by 37.9% while maintaining high sensitivity.
ACE-Net serves as a valuable clinical decision-making tool for thyroid cancer treatment planning.