A vision-language foundation model improves preoperative diagnosis of follicular thyroid neoplasms using ultrasound images

Preoperative discrimination between follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) remains challenging, as imaging and cytological approaches often show limited efficacy. Even fine-needle aspiration (FNA) biopsy and intraoperative frozen sections frequently fail to provide conclusive results. Thus, follicular thyroid neoplasms (FNs) typically necessitate complete surgical excision for definitive diagnosis, leading to unnecessary thyroidectomies for benign conditions or delayed treatment for malignancies. To address this gap, we developed FTC-Net, a vision-language foundation model, to preoperatively classify FNs using ultrasound images. In a multicenter retrospective study of 2421 patients (6477 images) from 14 institutions, FTC-Net was trained on 1462 patients and validated in two independent cohorts (n = 578 and n = 381). FTC-Net achieved AUCs of 0.836 and 0.841 in external validation, outperforming benchmark deep learning models and established TI-RADS systems. It also substantially reduced both total FNA rates and unnecessary FNA rates compared to ACR TI-RADS and C-TI-RADS. FTC-Net has the potential to serve as a non-invasive and advanced tool for the preoperative diagnosis of FNs, thereby improving clinical decision-making and reducing unnecessary procedures.

Authors

Institutions

Publication Details

Journal
npj Precision Oncology
Published
2026-04-16
DOI
https://doi.org/10.1038/s41698-026-01430-0
Primary Topic
Thyroid Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A vision-language foundation model improves preoperative diagnosis of follicular thyroid neoplasms using ultrasound images

Shuixing Zhang, Shuyi Liu, Jingjing You, Lizhu Ouyang et al.
npj Precision Oncology
Thyroid Cancer Diagnosis and Treatment
article

A vision-language foundation model improves preoperative diagnosis of follicular thyroid neoplasms using ultrasound images

Shuixing Zhang, Shuyi Liu, Jingjing You, Lizhu Ouyang, Guifeng Tu, Xiaoxiao Feng, B Zhang, Shufang Pei, Y Q Huang, Zhihong Lan, J I N Liu, Hui Shen, Fei Wang, Xin Chen, Bin Huang, Xuewei Wu, Kai Yang, Fei Guo, Ting Liang, Zhe Jin, Zhong Liu, Dan Yang, Wenle He, Lijuan Liu, Jie Sun, Yunjun Yang, Yingjia Li
article en

Abstract

Preoperative discrimination between follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) remains challenging, as imaging and cytological approaches often show limited efficacy. Even fine-needle aspiration (FNA) biopsy and intraoperative frozen sections frequently fail to provide conclusive results. Thus, follicular thyroid neoplasms (FNs) typically necessitate complete surgical excision for definitive diagnosis, leading to unnecessary thyroidectomies for benign conditions or delayed treatment for malignancies. To address this gap, we developed FTC-Net, a vision-language foundation model, to preoperatively classify FNs using ultrasound images. In a multicenter retrospective study of 2421 patients (6477 images) from 14 institutions, FTC-Net was trained on 1462 patients and validated in two independent cohorts (n = 578 and n = 381). FTC-Net achieved AUCs of 0.836 and 0.841 in external validation, outperforming benchmark deep learning models and established TI-RADS systems. It also substantially reduced both total FNA rates and unnecessary FNA rates compared to ACR TI-RADS and C-TI-RADS. FTC-Net has the potential to serve as a non-invasive and advanced tool for the preoperative diagnosis of FNs, thereby improving clinical decision-making and reducing unnecessary procedures.

npj Precision Oncology
Guangzhou University of Chinese Medicine (CN), Guilin Medical University (CN), Guangdong Medical College (CN), Shenzhen University (CN), Heidelberg University (DE), Kunming Medical University (CN), University Hospital Heidelberg (DE), First People's Hospital of Yunnan Province (CN), People’s Hospital of Wenshan Prefecture (CN), The First People's Hospital of Shunde (CN), Nanfang Hospital (CN), Zhuhai People's Hospital (CN), First People's Hospital of Foshan (CN), First Affiliated Hospital of Guangzhou University of Chinese Medicine (CN), National Center for Tumor Diseases (DE), First Affiliated Hospital of Kunming Medical University (CN), Foshan Second People's Hospital (CN), Shenzhen University Health Science Center (CN), Guangdong Academy of Medical Sciences (CN), First Affiliated Hospital of Jinan University (CN), Southern Medical University (CN), Guangzhou Medical University (CN)
National Natural Science Foundation of China, China Scholarship Council, Basic and Applied Basic Research Foundation of Guangdong Province
Peace, Justice and strong institutions
Openalex Percentile: Top 22%
Thyroid Cancer Diagnosis and Treatment
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.