Contrast-enhanced CT radiomics combined with multiple machine learning algorithms for preoperative identiﬁcation of lymph node metastasis in pancreatic ductal adenocarcinoma

Aug 5, 2026

Upload by Aria

Radiomics features extracted from contrast-enhanced CT were combined with multiple machine learning algorithms to improve preoperative identification of lymph node metastasis in pancreatic ductal adenocarcinoma (PDAC). A cohort of 128 pathologically confirmed PDAC patients undergoing surgical resection was randomized into training (n=93) and validation (n=35) sets. Thirteen algorithms and multiple combinations were evaluated using AUC, and the best-performing setup generated a Radscore, then integrated with clinical factors using multivariate logistic regression. Performance was assessed via ROC, calibration, and decision curve analysis.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Objectives

Methods

Results

Conclusions

Keywords

Introduction

TYPE Original Research PUBLISHED 13 September 2024 DOI 10.3389/fonc.2024.1342317 OPEN ACCESS EDITED BY Kuangyu Shi, University of Bern, Switzerland REVIEWED BY Ying Li, Fudan University, China Gang Ren, Air Force General Hospital PLA, China *CORRESPONDENCE Shangeng Weng [shangeng@sina.com](shangeng@sina.com) RECEIVED 22 November 2023 ACCEPTED 23 August 2024 PUBLISHED 13 September 2024 CITATION Huang Y, Zhang H, Chen L, Ding Q, Chen D, Liu G, Zhang X, Huang Q, Zhang D and Weng S (2024) Contrast-enhanced CT radiomics combined with multiple machine learning algorithms for preoperative identiﬁcation of lymph node metastasis in pancreatic ductal adenocarcinoma. Front. Oncol. 14:1342317 . doi: 10.3389/fonc.2024.1342317 COPYRIGHT © 2024 Huang, Zhang, Chen, Ding, Chen, Liu, Zhang, Huang, Zhang and Weng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Contrast-enhanced CT radiomics combined with multiple machine learning algorithms for preoperative identiﬁcation of lymph node metastasis in pancreatic ductal adenocarcinoma Yue Huang 1,2,3, Han Zhang 1,2,3, Lingfeng Chen 1,2,3, Qingzhu Ding 1,2,3, Dehua Chen 4, Guozhong Liu 1,3, Xiang Zhang 1,2,3, Qiang Huang 1,2,3, Denghan Zhang 1,2,3 and Shangeng Weng 1,2,3,5,6* 1 Department of Hepatopancreatobiliary Surgery, The First Afﬁliated Hospital of Fujian Medical University, Fuzhou, Fujian, China, 2Fujian Abdominal Surgery Research Institute, The First Afﬁliated Hospital of Fujian Medical University, Fuzhou, Fujian, China, 3 National Regional Medical Center, Binhai Campus of the First Afﬁliated Hospital, Fujian Medical University, Fuzhou, Fujian, China, 4 Department of Radiology, The First Afﬁliated Hospital of Fujian Medical University, Fuzhou, Fujian, China, 5 Fujian Provincial Key Laboratory of Precision Medicine for Cancer, The First Afﬁliated Hospital of Fujian Medical University, Fuzhou, Fujian, China, 6Clinical Research Center for Hepatobiliary Pancreatic and Gastrointestinal Malignant Tumors Precise Treatment of Fujian Province, The First Afﬁliated Hospital of Fujian Medical University, Fuzhou, Fujian, China Objectives: This research aimed to assess the value of radiomics combined with multiple machine learning algorithms in the diagnosis of pancreatic ductaladenocarcinoma (PDAC) lymph node (LN) metastasis, which is expected to provide clinical treatment strategies. Methods: A total of 128 patients with pathologically conﬁrmed PDAC and who underwent surgical resection were randomized into training (n=93) and validation (n=35) groups. This study incorporated a total of 13 distinct machine learning algorithms and explored 85 unique combinations of these algorithms. The area under the curve (AUC) of each model was computed. The model with the highest mean AUC was selected as the best model which was selected to determine the radiomics score (Radscore). The clinical factors were examined by the univariate and multivariate analysis, which allowed for the identiﬁcation offactors suitable for clinical modeling. The multivariate logistic regression was used to create a combined model using Radscore and clinical variables. The diagnostic performance was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA) . Results: Among the 233 models constructed using arterial phase (AP), venous phase (VP), and AP+VP radiomics features, the model built by applying AP+VP radiomics features and a combination of Lasso+Logistic algorithm had the highest mean AUC. A clinical model was eventually constructed using C

FAQs

What clinical problem does the study address?

The study evaluates radiomics features from contrast-enhanced CT combined with multiple machine learning algorithms for diagnosing lymph node metastasis before surgery.

How were patients and datasets organized?

Model selection and performance were compared across these cohorts.

Which model components produced the best diagnostic performance?

A clinical model was further built using CA199 and tumor size and then combined with Radscore in multivariate logistic regression.

Aug 5, 2026

Upload by Aria