Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE
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 ca...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
19 August 2025
|
| In: |
Cancer imaging
Year: 2025, Jahrgang: 25, Pages: 1-13 |
| ISSN: | 1470-7330 |
| DOI: | 10.1186/s40644-025-00926-5 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s40644-025-00926-5
|
| Verfasserangaben: | 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 and Osman Öcal |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1948934353 | ||
| 003 | DE-627 | ||
| 005 | 20260115123136.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 260115s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s40644-025-00926-5 |2 doi | |
| 035 | |a (DE-627)1948934353 | ||
| 035 | |a (DE-599)KXP1948934353 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Wei, Nan |e VerfasserIn |0 (DE-588)1386811297 |0 (DE-627)1948938502 |4 aut | |
| 245 | 1 | 0 | |a Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE |c 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 and Osman Öcal |
| 264 | 1 | |c 19 August 2025 | |
| 300 | |b Illustrationen | ||
| 300 | |a 13 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Veröffentlicht: 19. August 2025 | ||
| 500 | |a Gesehen am 15.01.2026 | ||
| 520 | |a 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. | ||
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a HCC | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Siamese network | |
| 650 | 4 | |a Tumor response | |
| 700 | 1 | |a Mathy, René Michael |e VerfasserIn |0 (DE-588)1225699282 |0 (DE-627)1745562877 |4 aut | |
| 700 | 1 | |a Chang, De-Hua |d 1978- |e VerfasserIn |0 (DE-588)132043939 |0 (DE-627)517295210 |0 (DE-576)298911752 |4 aut | |
| 700 | 1 | |a Mayer, Philipp |d 1985- |e VerfasserIn |0 (DE-588)1066605440 |0 (DE-627)817714758 |0 (DE-576)426052250 |4 aut | |
| 700 | 1 | |a Liermann, Jakob |d 1989- |e VerfasserIn |0 (DE-588)1147779287 |0 (DE-627)1007181842 |0 (DE-576)496034170 |4 aut | |
| 700 | 1 | |a Springfeld, Christoph |d 1972- |e VerfasserIn |0 (DE-588)123388910 |0 (DE-627)706281039 |0 (DE-576)293689385 |4 aut | |
| 700 | 1 | |a Dill, Michael T. |d 1983- |e VerfasserIn |0 (DE-588)1116508109 |0 (DE-627)871189305 |0 (DE-576)478447914 |4 aut | |
| 700 | 1 | |a Longerich, Thomas |d 1974- |e VerfasserIn |0 (DE-588)128494514 |0 (DE-627)373916124 |0 (DE-576)297178059 |4 aut | |
| 700 | 1 | |a Lurje, Georg |d 1979- |e VerfasserIn |0 (DE-588)136689949 |0 (DE-627)694581410 |0 (DE-576)301211744 |4 aut | |
| 700 | 1 | |a Kauczor, Hans-Ulrich |d 1962- |e VerfasserIn |0 (DE-588)139267123 |0 (DE-627)70327113X |0 (DE-576)310955327 |4 aut | |
| 700 | 1 | |a Wielpütz, Mark Oliver |d 1982- |e VerfasserIn |0 (DE-588)139999752 |0 (DE-627)614754682 |0 (DE-576)314127046 |4 aut | |
| 700 | 1 | |a Öcal, Osman |d 1989- |e VerfasserIn |0 (DE-588)1270864645 |0 (DE-627)1819701956 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Cancer imaging |d London : BioMed Central, 2000 |g 25(2025), Artikel-ID 104, Seite 1-13 |h Online-Ressource |w (DE-627)36374732X |w (DE-600)2104862-9 |w (DE-576)34726624X |x 1470-7330 |7 nnas |a Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE |
| 773 | 1 | 8 | |g volume:25 |g year:2025 |g elocationid:104 |g pages:1-13 |g extent:13 |a Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE |
| 856 | 4 | 0 | |u https://doi.org/10.1186/s40644-025-00926-5 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |7 0 |
| 951 | |a AR | ||
| 992 | |a 20260115 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1270864645 |a Öcal, Osman |m 1270864645:Öcal, Osman |d 910000 |d 911400 |e 910000PO1270864645 |e 911400PO1270864645 |k 0/910000/ |k 1/910000/911400/ |p 12 |y j | ||
| 998 | |g 139999752 |a Wielpütz, Mark Oliver |m 139999752:Wielpütz, Mark Oliver |d 50000 |e 50000PW139999752 |k 0/50000/ |p 11 | ||
| 998 | |g 139267123 |a Kauczor, Hans-Ulrich |m 139267123:Kauczor, Hans-Ulrich |d 910000 |d 911400 |e 910000PK139267123 |e 911400PK139267123 |k 0/910000/ |k 1/910000/911400/ |p 10 | ||
| 998 | |g 136689949 |a Lurje, Georg |m 136689949:Lurje, Georg |d 910000 |d 912000 |e 910000PL136689949 |e 912000PL136689949 |k 0/910000/ |k 1/910000/912000/ |p 9 | ||
| 998 | |g 128494514 |a Longerich, Thomas |m 128494514:Longerich, Thomas |d 910000 |d 912000 |e 910000PL128494514 |e 912000PL128494514 |k 0/910000/ |k 1/910000/912000/ |p 8 | ||
| 998 | |g 1116508109 |a Dill, Michael T. |m 1116508109:Dill, Michael T. |d 910000 |d 910100 |e 910000PD1116508109 |e 910100PD1116508109 |k 0/910000/ |k 1/910000/910100/ |p 7 | ||
| 998 | |g 123388910 |a Springfeld, Christoph |m 123388910:Springfeld, Christoph |d 910000 |d 910100 |d 50000 |e 910000PS123388910 |e 910100PS123388910 |e 50000PS123388910 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 6 | ||
| 998 | |g 1147779287 |a Liermann, Jakob |m 1147779287:Liermann, Jakob |d 910000 |d 911400 |d 50000 |e 910000PL1147779287 |e 911400PL1147779287 |e 50000PL1147779287 |k 0/910000/ |k 1/910000/911400/ |k 0/50000/ |p 5 | ||
| 998 | |g 1066605440 |a Mayer, Philipp |m 1066605440:Mayer, Philipp |d 910000 |d 911400 |e 910000PM1066605440 |e 911400PM1066605440 |k 0/910000/ |k 1/910000/911400/ |p 4 | ||
| 998 | |g 132043939 |a Chang, De-Hua |m 132043939:Chang, De-Hua |d 50000 |e 50000PC132043939 |k 0/50000/ |p 3 | ||
| 998 | |g 1225699282 |a Mathy, René Michael |m 1225699282:Mathy, René Michael |d 910000 |d 911400 |e 910000PM1225699282 |e 911400PM1225699282 |k 0/910000/ |k 1/910000/911400/ |p 2 | ||
| 998 | |g 1386811297 |a Wei, Nan |m 1386811297:Wei, Nan |d 50000 |e 50000PW1386811297 |k 0/50000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1948934353 |e 4849724086 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"recId":"1948934353","physDesc":[{"noteIll":"Illustrationen","extent":"13 S."}],"relHost":[{"pubHistory":["1.2000 -"],"origin":[{"publisherPlace":"London ; Heidelberg ; New York, NY","dateIssuedKey":"2000","dateIssuedDisp":"2000-","publisher":"BioMed Central ; BMC, part of Springer Nature"}],"part":{"year":"2025","pages":"1-13","extent":"13","text":"25(2025), Artikel-ID 104, Seite 1-13","volume":"25"},"title":[{"title_sort":"Cancer imaging","title":"Cancer imaging","subtitle":"the official publication of the International Cancer Imaging Society"}],"id":{"zdb":["2104862-9"],"eki":["36374732X"],"issn":["1470-7330"]},"note":["Gesehen am 20.03.23"],"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"recId":"36374732X","physDesc":[{"extent":"Online-Ressource"}],"disp":"Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACECancer imaging"}],"person":[{"display":"Wei, Nan","given":"Nan","role":"aut","family":"Wei"},{"display":"Mathy, René Michael","family":"Mathy","given":"René Michael","role":"aut"},{"display":"Chang, De-Hua","family":"Chang","role":"aut","given":"De-Hua"},{"given":"Philipp","role":"aut","family":"Mayer","display":"Mayer, Philipp"},{"display":"Liermann, Jakob","family":"Liermann","given":"Jakob","role":"aut"},{"display":"Springfeld, Christoph","family":"Springfeld","role":"aut","given":"Christoph"},{"display":"Dill, Michael T.","role":"aut","given":"Michael T.","family":"Dill"},{"display":"Longerich, Thomas","role":"aut","given":"Thomas","family":"Longerich"},{"display":"Lurje, Georg","role":"aut","given":"Georg","family":"Lurje"},{"display":"Kauczor, Hans-Ulrich","family":"Kauczor","given":"Hans-Ulrich","role":"aut"},{"display":"Wielpütz, Mark Oliver","family":"Wielpütz","role":"aut","given":"Mark Oliver"},{"family":"Öcal","given":"Osman","role":"aut","display":"Öcal, Osman"}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"19 August 2025"}],"title":[{"title":"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"}],"note":["Veröffentlicht: 19. August 2025","Gesehen am 15.01.2026"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"name":{"displayForm":["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 and Osman Öcal"]},"id":{"eki":["1948934353"],"doi":["10.1186/s40644-025-00926-5"]}} | ||
| SRT | |a WEINANMATHLONGITUDIN1920 | ||