EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning

Yuanzheng Lou, Yongjian Su, Haoda Lu, Wencai Li, Weihua Yin, Shengnan Li, Huobiao Zhu, Kok Haur Ong, Gang Chen, Yong Jiang, Yifei Liu, Shenglei Li und 16 weitere

Advanced Science · 2025-12 · 12 (48)

DOI: 10.1002/advs.202511369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 16.10.2025. Verfasst von Yuanzheng Lou und 27 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Nanfang Hospital and School of Basic Medical Sciences, Southern Medical University, Guangzhou, 510515, China. Hauptthemen laut MEDLINE: Thyroid Nodule, Deep Learning, Cytodiagnosis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Strategic Scientists Project of Jinfeng Laboratory, 2022 Major Science and Technology Innovation R&D Project of Chongqing Municipality, Major Project of Guangzhou National Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thyroid NoduleDeep LearningCytodiagnosisHumansBiopsy, Fine-NeedleFemaleChinaMaleMiddle AgedAdultThyroid GlandSensitivity and Specificity

Stichwörter der Autor:innen

artificial intelligencecytopathological diagnosisfine needle aspiration cytology (FNAC)thyroid noduleswhole‐slide image (WSI)

Autor:innen und Institutionen

  • Department of Pathology, Nanfang Hospital and School of Basic Medical Sciences, Southern Medical University, Guangzhou, 510515, China.
  • College of Bioengineering, Chongqing University, Chongqing, 400030, China.
  • Institute of Pathology & Southwest Cancer Center, the First Affiliated Hospital (Southwest Hospital) and School of Basic Medical Sciences, Army Medical University (Third Military Medical University), and the Key Laborat…
  • Chongqing Institute of Advanced Pathology, Jinfeng Laboratory, Chongqing, 400041, China.
  • Guangzhou F.Q. PATHOTECH Co., Ltd, Guangzhou, 510515, China.
  • Guangzhou Huayin Health Medical Group Co., Ltd, Guangzhou, 510663, China.

ORCID-Profile: Yanqing Ding

Förderung

  • Strategic Scientists Project of Jinfeng Laboratory
  • 2022 Major Science and Technology Innovation R&D Project of Chongqing Municipality
  • Major Project of Guangzhou National Laboratory
  • National Natural Science Foundation of China
  • 2023 Nantong Social Livelihood Science and Technology Plan Project
  • BMRC, A*STAR
  • Department of Pathology and Department of Biochemistry at NUS Yong Loo Lin School of Medicine
  • Industrial Alignment Funding - Pre-Positioning Grant

Zitieren

APA

Lou, Y., Su, Y., Lu, H., Li, W., Yin, W., Li, S., Zhu, H., Ong, K. H., Chen, G., Jiang, Y., Liu, Y., Li, S., Yang, M., Zhang, Z., Wang, X., Zhu, X., Huo, X., Li, L., Wang, C., …, & Ding, Y. (2025). Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning. Advanced Science, 12(48). https://doi.org/10.1002/advs.202511369

Vancouver

Lou Y, Su Y, Lu H, Li W, Yin W, Li S, et al. Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning. Advanced Science. 2025;12(48). doi:10.1002/advs.202511369

BibTeX
@article{Lou2025,
  author = {Lou, Yuanzheng and Su, Yongjian and Lu, Haoda and Li, Wencai and Yin, Weihua and Li, Shengnan and Zhu, Huobiao and Ong, Kok Haur and Chen, Gang and Jiang, Yong and Liu, Yifei and Li, Shenglei and Yang, Manchun and Zhang, Zhengyu and Wang, Xiaoyan and Zhu, Xiaohui and Huo, Xinmi and Li, Longjie and Wang, Chao and Zhang, Nanyan and Pan, Weijun and Shang, Bin and Yang, Xudan and Zhu, Yongqiang and Liu, Xiaolin and Yu, Weimiao and Bian, Xiuwu and Ding, Yanqing},
  title = {Cytological Classification Diagnosis for Thyroid Nodules via Multimodal Model Deep Learning},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {48},
  doi = {10.1002/advs.202511369}
}
Kostenlos starten →