Artificial intelligence-assisted precise preoperative prediction of lateral cervical lymph nodes metastasis in papillary thyroid carcinoma via a clinical-CT radiomic combined model

Sep 23, 2026

Uploaded by McQueen

Artificial intelligence-assisted modeling is used to predict preoperative lateral cervical lymph node metastasis (LCLNM) in papillary thyroid carcinoma (PTC) without invasive procedures. A retrospective cohort of 389 confirmed PTC patients was used to train and validate clinical-CT radiomics performance, with radiomic features extracted from contrast-enhanced CT images and clinical factors integrated into a combined model. Feature selection and multiple machine-learning algorithms were compared, and the best model achieved strong discriminative performance with decision-curve analysis supporting clinical utility for surgical planning.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Objectives

Methods

Results

Conclusions

Keywords

Artificial intelligence-assisted precise preoperative prediction of lateral cervical lymph nodes metastasis in papillary thyroid carcinoma via a clinical-CT radiomic combined model Junze Du, MMa , Xingyun He, BMb , Rui Fan, BMb , Yi Zhang, MDa , Hao Liu, PhDc , Haoxi Liu, MMd , * Shangqing Liu, PhDe , , Shichao Li, PhDa ,* Objectives: This study aimed to develop an artificial intelligence-assisted model for the preoperative prediction of lateral cervical lymph node metastasis (LCLNM) in papillary thyroid carcinoma (PTC) using computed tomography (CT) radiomics, providing a new noninvasive and accurate diagnostic tool for PTC patients with LCLNM. Methods: This retrospective study included 389 confirmed PTC patients, randomly divided into a training set (n = 272) and an internal validation set (n = 117), with an additional 40 patients from another hospital as an external validation set. Patient demographics were evaluated to establish a clinical model. Radiomic features were extracted from preoperative contrastenhanced CT images (venous phase) for each patient. Feature selection was performed using analysis of variance and the least absolute shrinkage and selection operator algorithm. We employed support vector machine, random forest (RF), logistic regression, and XGBoost algorithms to build CT radiomic models for predicting LCLNM. A radiomics score (Rad-score) was calculated using a radiomic signature-based formula. A combined clinical-radiomic model was then developed. The performance of the combined model was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) . Results: A total of 1724 radiomic features were extracted from each patient’s CT images, with 13 features selected based on nonzero coefficients related to LCLNM. Four clinically relevant factors (age, tumor location, thyroid capsule invasion, and central cervical lymph node metastasis) were significantly associated with LCLNM. Among the algorithms tested, the RF algorithm outperformed the others with five-fold cross-validation on the training set. After integrating the best algorithm with clinical factors, the areas under the ROC curves for the training, internal validation, and external validation sets were 0.910 (95% confidence interval [CI]: 0 .729–0.851), 0.876 (95% CI: 0.747–0.911), and 0.821 (95% CI: 0.555–0.802), respectively, with DCA demonstrating the clinical utility of the combined radiomic model. Conclusions: This study successfully established a clinical-CT radiomic combined model for predicting LCLNM, which may significantly enhance surgical decision-making for lateral cervical lymph node dissection in patients with PTC. Keywords: CT radiomics, lateral cervical lymph nodes metastasis, papillary thyroid carcinoma Introduction Thyroid cancer is the seventh most common cancer worldwide, with a significant increase in incidence over the last four decades[1] . Papillary thyroid carcinoma (PTC) accounts for aDepartment of Breast and Thyroid Surgery, Southwest Hospital, Army Medical University, Chongqing, China, bDepartment of Radiology, Southwest Hospital, Army Medical University, Chongqing, China, cYizhun Medical AI, Beijing, China, dDepartment of Breast and Thyroid Surgery, Guiqian International General Hospital, Guiyang, China and eCollege ofMedical Informatics, Chongqing Medical University, Chongqing, China J.D., X.H., and R.F. contributed equally to this work. Sponsorships or competing interests that may be relevant to content are disclosed at the end of this article. *Corresponding author. Address: Department of Breast and Thyroid Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, China. E-mail: [shichaoli@tmmu.edu.cn](shichaoli@tmmu.edu.cn) (S. Li); College of Medical Informatics, Chongqing Medical University, Chongqing 400016, [China. E-mail: shangqingliu@cqmu.edu.cn](China. E-mail: shangqingliu@cqmu.edu.cn) (S. Liu). Copyright © 2025 T

FAQs

What is the main objective of the study?

To develop an AI-assisted clinical-CT radiomic combined model for precise preoperative prediction of lateral cervical lymph node metastasis (LCLNM) in papillary thyroid carcinoma (PTC).

How were radiomic features and clinical factors used in the model?

Radiomic features were extracted from preoperative contrast-enhanced CT images (venous phase), selected via statistical and LASSO-based methods, and combined with clinically relevant factors including age, tumor location, thyroid capsule invasion, and central cervical lymph node metastasis.

Which algorithm performed best and how was performance evaluated?

Random forest (RF) outperformed other tested algorithms in five-fold cross-validation. Performance was assessed using ROC curves, calibration curves, and decision curve analysis (DCA) across training, internal validation, and external validation sets.

Sep 23, 2026

Uploaded by McQueen