Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning

The rising prevalence of thyroid nodules is straining limited cytopathology resources, resulting in excessive overdiagnosis and overtreatment with significant patient and healthcare consequences. To address this, AI-TFNA is developed, a robust artificial intelligence platform leveraging extensive clinical data to enhance diagnostic accuracy and clinical efficiency. A total of 20,803 thyroid samples are collected from seven medical centers across different regions in China. Of these, 4,421 thyroid fine-needle aspiration (TFNA) samples from three hospitals are used to train AI-TFNA, ensuring strong generalizability across diverse clinical settings. For the internal validation, AI-TFNA demonstrates exceptional performance: the overall accuracy of TBS I is 93.27%, the sensitivity of TBS V and TBS VI reaches 85.37% and 83.78%, while the specificity of TBS II is 97.13%. Consistent results are observed in an external cohort of 2,153 samples, demonstrating robust generalizability. The incorporation of BRAF mutation data into AI-TFNA and the development of a multi-modal model further improve precision by significantly improving the differentiation between benign and malignant thyroid nodules. Image Appearance Migration (IAM) is an innovative technique that substantially improves cross-institutional model generalizability, increasing AI-TFNA sensitivity by 1.90% and specificity by 8.12%. AI-TFNA offers rapid, reliable decision support, advancing thyroid nodule diagnostics.

Authors

Institutions

Publication Details

Journal
Advanced Science
Published
2025-10-16
DOI
https://doi.org/10.1002/advs.202511369
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

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

Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning

Yanqing Ding, Xiu‐Wu Bian, Xiaoyan Wang, Weimiao Yu et al.
Advanced Science
AI in cancer detection
article

Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning

Yanqing Ding, Xiu‐Wu Bian, Xiaoyan Wang, Weimiao Yu, Yifei Liu, Longjie Li, Haoda Lu, Huobiao Zhu, Wencai Li, Xinmi Huo, Xiaohui Zhu, Bin Shang, Shengnan Li, Yong Jiang, Kok Haur Ong, Weihua Yin, Xiaolin Liu, Chao Wang, Yongqiang Zhu, Manchun Yang, Shenglei Li, Xudan Yang, Weijun Pan, Yaxin Lou, Nanyan Zhang, Zhengyu Zhang, Gang Chen, Yongjian Su
article en

Abstract

The rising prevalence of thyroid nodules is straining limited cytopathology resources, resulting in excessive overdiagnosis and overtreatment with significant patient and healthcare consequences. To address this, AI-TFNA is developed, a robust artificial intelligence platform leveraging extensive clinical data to enhance diagnostic accuracy and clinical efficiency. A total of 20,803 thyroid samples are collected from seven medical centers across different regions in China. Of these, 4,421 thyroid fine-needle aspiration (TFNA) samples from three hospitals are used to train AI-TFNA, ensuring strong generalizability across diverse clinical settings. For the internal validation, AI-TFNA demonstrates exceptional performance: the overall accuracy of TBS I is 93.27%, the sensitivity of TBS V and TBS VI reaches 85.37% and 83.78%, while the specificity of TBS II is 97.13%. Consistent results are observed in an external cohort of 2,153 samples, demonstrating robust generalizability. The incorporation of BRAF mutation data into AI-TFNA and the development of a multi-modal model further improve precision by significantly improving the differentiation between benign and malignant thyroid nodules. Image Appearance Migration (IAM) is an innovative technique that substantially improves cross-institutional model generalizability, increasing AI-TFNA sensitivity by 1.90% and specificity by 8.12%. AI-TFNA offers rapid, reliable decision support, advancing thyroid nodule diagnostics.

Advanced ScienceVol. 12(48)
Agency for Science, Technology and Research (SG), Fujian Medical University (CN), University of Electronic Science and Technology of China (CN), Army Medical University (CN), Chongqing University (CN), Nantong University (CN), Sichuan University (CN), Affiliated Hospital of Nantong University (CN), West China Hospital of Sichuan University (CN), Key Laboratory of Guangdong Province (CN), RayBiotech (China) (CN), Chongqing 2D Materials Institute (China) (CN), Peking University Shenzhen Hospital (CN), Southwest Hospital (CN), Bioinformatics Institute (SG), Fujian Provincial Cancer Hospital (CN), First Affiliated Hospital of Zhengzhou University (CN), Southern Medical University (CN), Institute of Molecular and Cell Biology (SG), Guangzhou Medical University (CN)
National Natural Science Foundation of China, Centre Scientifique et Technique du Bâtiment, Directorate for Biological Sciences, Institute of Molecular and Cell Biology, Biomedical Research Council
Openalex Percentile: Top 85%
AI in cancer detection
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.