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

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.

Authors

Institutions

Publication Details

Journal
Thyroid
Published
2026-11-18
DOI
https://doi.org/10.1177/10507256261502920
Citations
1
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
2.33

Funders

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

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

Jia Qi, Hao Xiong, W. Li, Yisikandaer Yalikun et al.
1 citations
Thyroid
Radiomics and Machine Learning in Medical Imaging
2.33
article

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

Jia Qi, Hao Xiong, W. Li, Yisikandaer Yalikun, Yaying Du, Hanning Li, Xingyin Li, Yuan Su, Xi Chen, Yulin Li, Xingmin Yan, yiqing xi, Zhihao Wei, Ziying Chen, Shaojie Xu, Jiamei Jiang, Xingrui Li
article en
1 citations

Abstract

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.

Thyroid
Tianjin Medical University General Hospital (CN), Third Affiliated Hospital of Sun Yat-sen University (CN), Tongji Hospital (CN), Hubei Cancer Hospital (CN), Yulin Orthopedics Hospital of Chinese and Western Medicine (CN), Huazhong University of Science and Technology (CN), Chongqing Medical University (CN)
National Natural Science Foundation of China, Natural Science Foundation of Hubei Province, Tongji University
Good health and well-being
Openalex Percentile: Top 20%
Radiomics and Machine Learning in Medical Imaging
2.33
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.

Laika access coming soon