CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study

Abstract Objective Platinum resistance carries poor prognosis in epithelial ovarian carcinoma (EOC). This study aimed to assess the value of radiomics model based on contrast-enhanced CT (ceCT) in predicting response to platinum-based chemotherapy in EOC. Materials and methods Patients with histolog...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengge He, Rahul Singh, Mandi Wang, Grace Ho, Esther M. F. Wong, Keith W. H. Chiu, Anthony K. T. Leung, Ka Yu Tse, Philip P. C. Ip, Andy Hwang, Lujun Han, Elaine Y. P. Lee
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Cancer Imaging
Subjects:
Online Access:https://doi.org/10.1186/s40644-025-00906-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334417329225728
author Mengge He
Rahul Singh
Mandi Wang
Grace Ho
Esther M. F. Wong
Keith W. H. Chiu
Anthony K. T. Leung
Ka Yu Tse
Philip P. C. Ip
Andy Hwang
Lujun Han
Elaine Y. P. Lee
author_facet Mengge He
Rahul Singh
Mandi Wang
Grace Ho
Esther M. F. Wong
Keith W. H. Chiu
Anthony K. T. Leung
Ka Yu Tse
Philip P. C. Ip
Andy Hwang
Lujun Han
Elaine Y. P. Lee
author_sort Mengge He
collection DOAJ
description Abstract Objective Platinum resistance carries poor prognosis in epithelial ovarian carcinoma (EOC). This study aimed to assess the value of radiomics model based on contrast-enhanced CT (ceCT) in predicting response to platinum-based chemotherapy in EOC. Materials and methods Patients with histologically confirmed EOC and pre-treatment ceCT were retrospectively recruited from 5 centres. All patients underwent standard platinum-based chemotherapy and optimal cytoreduction. Platinum sensitivity was determined by whether it recurred within six months after platinum-based chemotherapy. The whole tumour volume was manually segmented on the baseline ceCT. Radiomics features were extracted using the open-source package PyRadiomics (version 3.0.1). Patients from centres A-C were randomly divided into training and internal validation sets in 4:1 ratio. Patients from the centres D and E were assigned as independent external validation sets. Spearman’s rank correlation followed by 5-fold stratified cross validation (SCV) elastic net repeated for 100 times, and Mann-Whitney U test were deployed for feature reduction and selection. Adaptive synthetic sampling was applied to minimize class biases. Extra Trees classifier across 10-fold SCV was used for model building. The area under curve (AUC), calibration curve assessment, and decision curve analysis (DCA) were deployed to evaluate model performance and translational clinical utility. Results Seven hundred and three EOC patients (51.6 ± 9.3 years) were recruited. The training data (n = 608) yielded the following classification metrics: AUC (0.917), sensitivity (83.9%), specificity (94.4%), and accuracy (91.7%) in the internal validation set. The external validation set using centre D (n = 44) had AUC (0.877), sensitivity (76.5%), specificity (92.6%), and accuracy (86.4%); while centre E (n = 51) had AUC (0.845), sensitivity (73.3%), specificity (86.1%), and accuracy (82.4%) in predicting platinum sensitivity. DCA illustrated net clinical benefit in internal validation set and both external validation sets. Conclusions The proposed CT-based radiomics model could be useful in predicting platinum sensitivity in EOC with potential in guiding personalized treatment in EOC.
format Article
id doaj-art-ad58bb4ff6214712b401aa3d0dd71d9d
institution Kabale University
issn 1470-7330
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Cancer Imaging
spelling doaj-art-ad58bb4ff6214712b401aa3d0dd71d9d2025-08-20T03:45:34ZengBMCCancer Imaging1470-73302025-07-0125111310.1186/s40644-025-00906-9CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre studyMengge He0Rahul Singh1Mandi Wang2Grace Ho3Esther M. F. Wong4Keith W. H. Chiu5Anthony K. T. Leung6Ka Yu Tse7Philip P. C. Ip8Andy Hwang9Lujun Han10Elaine Y. P. Lee11Department of Diagnostic Radiology, The University of Hong KongDepartment of Diagnostic Radiology, The University of Hong KongDepartment of Diagnostic Radiology, The University of Hong KongDepartment of Radiology, Queen Mary HospitalDepartment of Radiology, Pamela Youde Nethersole Eastern HospitalDepartment of Radiology & Imaging, Queen Elizabeth HospitalDepartment of Clinical Oncology, Queen Elizabeth HospitalDepartment of Obstetrics and Gynecology, The University of Hong KongDepartment of Pathology, The University of Hong KongDepartment of Diagnostic Radiology, The University of Hong KongDepartment of Radiology, Sun Yat-Sen University Cancer CentreDepartment of Diagnostic Radiology, The University of Hong KongAbstract Objective Platinum resistance carries poor prognosis in epithelial ovarian carcinoma (EOC). This study aimed to assess the value of radiomics model based on contrast-enhanced CT (ceCT) in predicting response to platinum-based chemotherapy in EOC. Materials and methods Patients with histologically confirmed EOC and pre-treatment ceCT were retrospectively recruited from 5 centres. All patients underwent standard platinum-based chemotherapy and optimal cytoreduction. Platinum sensitivity was determined by whether it recurred within six months after platinum-based chemotherapy. The whole tumour volume was manually segmented on the baseline ceCT. Radiomics features were extracted using the open-source package PyRadiomics (version 3.0.1). Patients from centres A-C were randomly divided into training and internal validation sets in 4:1 ratio. Patients from the centres D and E were assigned as independent external validation sets. Spearman’s rank correlation followed by 5-fold stratified cross validation (SCV) elastic net repeated for 100 times, and Mann-Whitney U test were deployed for feature reduction and selection. Adaptive synthetic sampling was applied to minimize class biases. Extra Trees classifier across 10-fold SCV was used for model building. The area under curve (AUC), calibration curve assessment, and decision curve analysis (DCA) were deployed to evaluate model performance and translational clinical utility. Results Seven hundred and three EOC patients (51.6 ± 9.3 years) were recruited. The training data (n = 608) yielded the following classification metrics: AUC (0.917), sensitivity (83.9%), specificity (94.4%), and accuracy (91.7%) in the internal validation set. The external validation set using centre D (n = 44) had AUC (0.877), sensitivity (76.5%), specificity (92.6%), and accuracy (86.4%); while centre E (n = 51) had AUC (0.845), sensitivity (73.3%), specificity (86.1%), and accuracy (82.4%) in predicting platinum sensitivity. DCA illustrated net clinical benefit in internal validation set and both external validation sets. Conclusions The proposed CT-based radiomics model could be useful in predicting platinum sensitivity in EOC with potential in guiding personalized treatment in EOC.https://doi.org/10.1186/s40644-025-00906-9Epithelial ovarian carcinomaComputed tomographyRadiomicsChemotherapyPlatinum-Resistance
spellingShingle Mengge He
Rahul Singh
Mandi Wang
Grace Ho
Esther M. F. Wong
Keith W. H. Chiu
Anthony K. T. Leung
Ka Yu Tse
Philip P. C. Ip
Andy Hwang
Lujun Han
Elaine Y. P. Lee
CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
Cancer Imaging
Epithelial ovarian carcinoma
Computed tomography
Radiomics
Chemotherapy
Platinum-Resistance
title CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
title_full CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
title_fullStr CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
title_full_unstemmed CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
title_short CT-based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma: a multicentre study
title_sort ct based radiomics model to predict platinum sensitivity in epithelial ovarian carcinoma a multicentre study
topic Epithelial ovarian carcinoma
Computed tomography
Radiomics
Chemotherapy
Platinum-Resistance
url https://doi.org/10.1186/s40644-025-00906-9
work_keys_str_mv AT menggehe ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT rahulsingh ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT mandiwang ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT graceho ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT esthermfwong ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT keithwhchiu ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT anthonyktleung ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT kayutse ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT philippcip ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT andyhwang ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT lujunhan ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy
AT elaineyplee ctbasedradiomicsmodeltopredictplatinumsensitivityinepithelialovariancarcinomaamulticentrestudy