EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Multicenter CT-Based Deep Learning for Preoperative Nodal Risk Stratification in Papillary Thyroid Carcinoma

Shaojie Xu iD, Xingmin Yan, Yuhang Su, Jia Qi, Xingyu Chen, Yulin Li, Hao Xiong, Jiamei Jiang, Zhihao Wei, Ziying Chen, Yisikandaer Yalikun, Hanning Li und 5 weitere

Thyroid® · 18.11.2026

DOI: 10.1177/10507256261502920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Thyroid®, online erschienen am 18.11.2026. Verfasst von Shaojie Xu und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thyroid and Breast Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Hubei Chutian Talents Entrepreneurship and Innovation Team, Natural Science Foundation of Hubei Province, Medical Artificial Intelligence General Program of Tongji Hospital 2025.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate preoperative risk stratification for lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) remains difficult. We developed and validated ThyLNT, a Transformer-based 2.5D deep learning model using preoperative computed tomography (CT), and explored related biological features in multi-omics analyses.

Methods

A total of 1560 patients with PTC from six hospitals were retrospectively included. The Tongji Hospital cohort was divided into training and internal validation sets, and five external cohorts were used for independent testing. Seven 2.5D tumor slices were extracted per patient, encoded with a DenseNet201 backbone, and fused by a Transformer. Model performance was compared with radiomics, ensemble learning, and multi-instance learning using AUC, calibration, decision curve, and precision-recall analyses. Bulk RNA-seq, single-cell RNA-seq, spatial transcriptomics, and spatial metabolomics were used to explore related biological features.

Results

ThyLNT achieved an AUC of 0.882 (CI, 0.858–0.905) in the training cohort, 0.787 (CI, 0.738–0.835) in the internal validation cohort, and 0.772 (CI, 0.662–0.878) to 0.827 (CI, 0.763–0.885) across the five external cohorts. It showed multicenter discrimination, whereas calibration and threshold-dependent operating characteristics varied across cohorts. Multi-omics analyses provided exploratory biological context, including candidate associations with vascular endothelial growth factor A-related signaling and lipid metabolism.

Conclusions

ThyLNT demonstrated multicenter performance for preoperative LNM prediction in PTC and may support risk stratification, although calibration, threshold use, and clinical utility require prospective validation.

Schlagwörter

Stichwörter der Autor:innen

computed tomographydeep learninglymph node metastasispapillary thyroid carcinomatransformer

Autor:innen und Institutionen

  • Department of Thyroid and Breast Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Division of Hepato-Pancreato-Biliary Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Department of Thyroid and Breast Surgery, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China.
  • Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Radiology Department, Nanchuan Hospital of Chongqing Medical University, Chongqing, China.
  • Radiology Department, Red Cross Hospital of Yulin City, Yulin, China.

ORCID-Profile: Shaojie Xu

Förderung

  • Hubei Chutian Talents Entrepreneurship and Innovation Team
  • Natural Science Foundation of Hubei Province
  • Medical Artificial Intelligence General Program of Tongji Hospital 2025
  • National Natural Science Foundation of China
  • Qingyan Fund – Young Scholars Development Program

Zitieren

APA

Xu, S., Yan, X., Su, Y., Qi, J., Chen, X., Li, Y., Xiong, H., Jiang, J., Wei, Z., Chen, Z., Yalikun, Y., Li, H., Li, X., Xi, Y., Li, W., Li, X., & Du, Y. (2026). Multicenter CT-Based Deep Learning for Preoperative Nodal Risk Stratification in Papillary Thyroid Carcinoma. Thyroid®. https://doi.org/10.1177/10507256261502920

Vancouver

Xu S, Yan X, Su Y, Qi J, Chen X, Li Y, et al. Multicenter CT-Based Deep Learning for Preoperative Nodal Risk Stratification in Papillary Thyroid Carcinoma. Thyroid®. 2026. doi:10.1177/10507256261502920

BibTeX
@article{Xu2026,
  author = {Xu, Shaojie and Yan, Xingmin and Su, Yuhang and Qi, Jia and Chen, Xingyu and Li, Yulin and Xiong, Hao and Jiang, Jiamei and Wei, Zhihao and Chen, Ziying and Yalikun, Yisikandaer and Li, Hanning and Li, Xingyin and Xi, Yiqing and Li, Wei and Li, Xingrui and Du, Yaying},
  title = {Multicenter CT-Based Deep Learning for Preoperative Nodal Risk Stratification in Papillary Thyroid Carcinoma},
  journal = {Thyroid®},
  year = {2026},
  doi = {10.1177/10507256261502920}
}
Kostenlos starten →