Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE

Abstract Background Accurate prediction of tumor response after drug-eluting beads transarterial chemoembolization (DEB-TACE) remains challenging in hepatocellular carcinoma (HCC), given tumor heterogeneity and dynamic changes over time. Existing prediction models based on single timepoint imaging d...

Full description

Saved in:
Bibliographic Details
Main Authors: Nan Wei, René Michael Mathy, De-Hua Chang, Philipp Mayer, Jakob Liermann, Christoph Springfeld, Michael T Dill, Thomas Longerich, Georg Lurje, Hans-Ulrich Kauczor, Mark O. Wielpütz, Osman Öcal
Format: Article
Language:English
Published: BMC 2025-08-01
Series:Cancer Imaging
Subjects:
Online Access:https://doi.org/10.1186/s40644-025-00926-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225965680459776
author Nan Wei
René Michael Mathy
De-Hua Chang
Philipp Mayer
Jakob Liermann
Christoph Springfeld
Michael T Dill
Thomas Longerich
Georg Lurje
Hans-Ulrich Kauczor
Mark O. Wielpütz
Osman Öcal
author_facet Nan Wei
René Michael Mathy
De-Hua Chang
Philipp Mayer
Jakob Liermann
Christoph Springfeld
Michael T Dill
Thomas Longerich
Georg Lurje
Hans-Ulrich Kauczor
Mark O. Wielpütz
Osman Öcal
author_sort Nan Wei
collection DOAJ
description Abstract Background Accurate prediction of tumor response after drug-eluting beads transarterial chemoembolization (DEB-TACE) remains challenging in hepatocellular carcinoma (HCC), given tumor heterogeneity and dynamic changes over time. Existing prediction models based on single timepoint imaging do not capture dynamic treatment-induced changes. This study aims to develop and validate a predictive model that integrates deep learning and machine learning algorithms on longitudinal contrast-enhanced MRI (CE-MRI) to predict treatment response in HCC patients undergoing DEB-TACE. Methods This retrospective study included 202 HCC patients treated with DEB-TACE from 2004 to 2023, divided into a training cohort (n = 141) and validation cohort (n = 61). Radiomics and deep learning features were extracted from standardized longitudinal CE-MRI to capture dynamic tumor changes. Feature selection involved correlation analysis, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator regression. The patients were categorized into two groups: the objective response group (n = 123, 60.9%; complete response = 35, 28.5%; partial response = 88, 71.5%) and the non-response group (n = 79, 39.1%; stable disease = 62, 78.5%; progressive disease = 17, 21.5%). Predictive models were constructed using radiomics, deep learning, and integrated features. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the models. Results We retrospectively evaluated 202 patients (62.67 ± 9.25 years old) with HCC treated after DEB-TACE. A total of 7,182 radiomics features and 4,096 deep learning features were extracted from the longitudinal CE-MRI images. The integrated model was developed using 13 quantitative radiomics features and 4 deep learning features and demonstrated acceptable and robust performance with an receiver operating characteristic curve (AUC) of 0.941 (95%CI: 0.893–0.989) in the training cohort, and AUC of 0.925 (95%CI: 0.850–0.998) with accuracy of 86.9%, sensitivity of 83.7%, as well as specificity of 94.4% in the validation set. Conclusions This study presents a predictive model based on longitudinal CE-MRI data to estimate tumor response to DEB-TACE in HCC patients. By capturing tumor dynamics and integrating radiomics features with deep learning features, the model has the potential to guide individualized treatment strategies and inform clinical decision-making regarding patient management.
format Article
id doaj-art-1718e2b508ab410d9cc24144b8a472ec
institution Kabale University
issn 1470-7330
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series Cancer Imaging
spelling doaj-art-1718e2b508ab410d9cc24144b8a472ec2025-08-24T11:48:20ZengBMCCancer Imaging1470-73302025-08-0125111310.1186/s40644-025-00926-5Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACENan Wei0René Michael Mathy1De-Hua Chang2Philipp Mayer3Jakob Liermann4Christoph Springfeld5Michael T Dill6Thomas Longerich7Georg Lurje8Hans-Ulrich Kauczor9Mark O. Wielpütz10Osman Öcal11Department of Diagnostic and Interventional Radiology, University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergLiver Cancer Center HeidelbergLiver Cancer Center HeidelbergLiver Cancer Center HeidelbergNational Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and University Hospital of HeidelbergNational Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergDepartment of Diagnostic and Interventional Radiology, University Hospital of HeidelbergAbstract Background Accurate prediction of tumor response after drug-eluting beads transarterial chemoembolization (DEB-TACE) remains challenging in hepatocellular carcinoma (HCC), given tumor heterogeneity and dynamic changes over time. Existing prediction models based on single timepoint imaging do not capture dynamic treatment-induced changes. This study aims to develop and validate a predictive model that integrates deep learning and machine learning algorithms on longitudinal contrast-enhanced MRI (CE-MRI) to predict treatment response in HCC patients undergoing DEB-TACE. Methods This retrospective study included 202 HCC patients treated with DEB-TACE from 2004 to 2023, divided into a training cohort (n = 141) and validation cohort (n = 61). Radiomics and deep learning features were extracted from standardized longitudinal CE-MRI to capture dynamic tumor changes. Feature selection involved correlation analysis, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator regression. The patients were categorized into two groups: the objective response group (n = 123, 60.9%; complete response = 35, 28.5%; partial response = 88, 71.5%) and the non-response group (n = 79, 39.1%; stable disease = 62, 78.5%; progressive disease = 17, 21.5%). Predictive models were constructed using radiomics, deep learning, and integrated features. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the models. Results We retrospectively evaluated 202 patients (62.67 ± 9.25 years old) with HCC treated after DEB-TACE. A total of 7,182 radiomics features and 4,096 deep learning features were extracted from the longitudinal CE-MRI images. The integrated model was developed using 13 quantitative radiomics features and 4 deep learning features and demonstrated acceptable and robust performance with an receiver operating characteristic curve (AUC) of 0.941 (95%CI: 0.893–0.989) in the training cohort, and AUC of 0.925 (95%CI: 0.850–0.998) with accuracy of 86.9%, sensitivity of 83.7%, as well as specificity of 94.4% in the validation set. Conclusions This study presents a predictive model based on longitudinal CE-MRI data to estimate tumor response to DEB-TACE in HCC patients. By capturing tumor dynamics and integrating radiomics features with deep learning features, the model has the potential to guide individualized treatment strategies and inform clinical decision-making regarding patient management.https://doi.org/10.1186/s40644-025-00926-5Deep learningMachine learningSiamese networkHCCTumor response
spellingShingle Nan Wei
René Michael Mathy
De-Hua Chang
Philipp Mayer
Jakob Liermann
Christoph Springfeld
Michael T Dill
Thomas Longerich
Georg Lurje
Hans-Ulrich Kauczor
Mark O. Wielpütz
Osman Öcal
Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
Cancer Imaging
Deep learning
Machine learning
Siamese network
HCC
Tumor response
title Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
title_full Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
title_fullStr Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
title_full_unstemmed Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
title_short Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
title_sort longitudinal ce mri based siamese network with machine learning to predict tumor response in hcc after deb tace
topic Deep learning
Machine learning
Siamese network
HCC
Tumor response
url https://doi.org/10.1186/s40644-025-00926-5
work_keys_str_mv AT nanwei longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT renemichaelmathy longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT dehuachang longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT philippmayer longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT jakobliermann longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT christophspringfeld longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT michaeltdill longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT thomaslongerich longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT georglurje longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT hansulrichkauczor longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT markowielputz longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace
AT osmanocal longitudinalcemribasedsiamesenetworkwithmachinelearningtopredicttumorresponseinhccafterdebtace