Prediction of angiogenesis in extrahepatic cholangiocarcinoma using MRI-based machine learning - Original Research

Q: What clinical objective does the study address?

To provide a reliable noninvasive preoperative method for predicting angiogenesis in extrahepatic cholangiocarcinoma.

Q: How are VEGF expression and microvessel density predicted?

MRI features are extracted from T1-, T2-, and diffusion-weighted images and used to build a classification model for VEGF expression and a regression model for microvessel density.

Q: What model configurations showed strong performance?

Z-score standardization combined with logistic regression performed excellently for VEGF prediction, while Z-score standardization combined with stochastic gradient descent-based linear regression performed well for MVD regression.

Aug 3, 2026

Upload by Logic

Reliable noninvasive assessment is needed for preoperative prediction of angiogenesis in extrahepatic cholangiocarcinoma (eCCA). This retrospective study developed and validated machine learning models using MRI radiomics from T1-, T2-, and diffusion-weighted images to predict vascular endothelial growth factor (VEGF) expression and to model microvessel density (MVD). Feature selection based on reliability screening supported separate classification and regression pipelines.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Purpose

Materials and methods

Feature extraction and modeling

Evaluation metrics

Results

Conclusion

TYPE Original Research PUBLISHED 18 May 2023 DOI 10.3389/fonc.2023.1048311 OPEN ACCESS EDITED BY Daniel Neureiter, Salzburger Landeskliniken, Austria REVIEWED BY Zhiyu Xiao, Sun Yat-Sen University, China Tian-wu Chen, Afﬁliated Hospital of North Sichuan Medical College, China *CORRESPONDENCE Jian Shu [shujiannc@163.com](shujiannc@163.com) †These authors have contributed equally to this work RECEIVED 19 September 2022 ACCEPTED 28 April 2023 PUBLISHED 18 May 2023 CITATION Liu J, Liu M, Gong Y, Su S, Li M and Shu J (2023) Prediction of angiogenesis in extrahepatic cholangiocarcinoma using MRI-based machine learning. Front. Oncol. 13:1048311 . doi: 10.3389/fonc.2023.1048311 COPYRIGHT © 2023 Liu, Liu, Gong, Su, Li and Shu. This isan 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. Prediction of angiogenesis in extrahepatic cholangiocarcinoma using MRIbased machine learning Jiong Liu 1,2†, Mali Liu 1,2†, Yaolin Gong 1,2, Song Su 3, Man Li 4 and Jian Shu 1,2* 1 Department of Radiology, The Afﬁliated Hospital of Southwest Medical University, Luzhou, Sichuan, China, 2 Nuclear Medicine and Molecular Imaging Key Laboratory of Sichuan Province, Luzhou, Sichuan, China, 3 Department of Hepatobiliary Surgery, The Afﬁliated Hospital of Southwest Medical University, Luzhou, China, 4 Department of Research and Development, Shanghai United Imaging Intelligence Co., Shanghai, China Purpose: Reliable noninvasive method to preoperative prediction of extrahepatic cholangiocarcinoma (eCCA) angiogenesis are needed. This study aims to develop and validate machine learning models based on magnetic resonance imaging (MRI) for predicting vascular endothelial growth factor (VEGF) expression and the microvessel density (MVD) of eCCA. Materials and methods: In this retrospective study from August 2011 to May 2020, eCCA patients with pathological conﬁrmation were selected. Features were extracted from T1-weighted, T2-weighted, and diffusion-weighted images using the MaZda software. After reliability testing and feature screening, retained features were used to establish classiﬁcation models for predicting VEGF expression and regression models for predicting MVD. The performance of both models was evaluated respectively using area under the curve (AUC) and Adjusted R-Squared (Adjusted R2) . Results: The machine learning models were developed in 100 patients. A total of 900 features were extracted and 77 features with intraclass correlation coefﬁcient (ICC) < 0 .75 were eliminated. Among all the combinations of data preprocessing methods and classiﬁcation algorithms, Z-score standardization + logistic regression exhibited excellent ability both in the training cohort (average AUC = 0 . 912) and the testing cohort (average AUC = 0 . 884) . For regression model, Z-score standardization + stochastic gradient descent-based linear regression performed well in the training cohort (average Adjusted R2 = 0. 975), and was also better than the mean model in the test cohort (average Adjusted R2 = 0.781) . Conclusion: Two machine learning models based on MRI can accurately predict VEGF expression and the MVD of eCCA respectively. KEYWORDS cholangiocarcinoma, magnetic resonance imaging, machine learning, vascular endothelial growth factor, microvessel density Frontiers in Oncology 01 [frontiersin.org](frontiersin.org) 1 Introduction Cholangiocarcinoma (CCA) is a group of highly heterogeneous malignancies. CCA can be divided into three subtypes: intrahepatic cholangiocarcinoma (iCCA), perihilar cholangiocarcinoma (pCCA) and dist

FAQs

What clinical objective does the study address?

To provide a reliable noninvasive preoperative method for predicting angiogenesis in extrahepatic cholangiocarcinoma.

How are VEGF expression and microvessel density predicted?

MRI features are extracted from T1-, T2-, and diffusion-weighted images and used to build a classification model for VEGF expression and a regression model for microvessel density.

What model configurations showed strong performance?

Z-score standardization combined with logistic regression performed excellently for VEGF prediction, while Z-score standardization combined with stochastic gradient descent-based linear regression performed well for MVD regression.

Aug 3, 2026

Upload by Logic