Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics

A significant proportion of locally advanced cervical cancer (LACC) patients experience disease progression post chemoradiotherapy (CRT). Currently existing clinical variables are suboptimal predictors of treatment response. This study reported a radiomics-based model leveraging information extracte...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Clinical oncology (Royal College of Radiologists (Great Britain)) 2025-02, Vol.38, p.103702, Article 103702
Hauptverfasser: Tang, S., Yen, A., Wang, K., Albuquerque, K., Wang, J.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page 103702
container_title Clinical oncology (Royal College of Radiologists (Great Britain))
container_volume 38
creator Tang, S.
Yen, A.
Wang, K.
Albuquerque, K.
Wang, J.
description A significant proportion of locally advanced cervical cancer (LACC) patients experience disease progression post chemoradiotherapy (CRT). Currently existing clinical variables are suboptimal predictors of treatment response. This study reported a radiomics-based model leveraging information extracted from magnetic resonance (MR) T2-weighted image (T2WI) to predict the progression-free survival (PFS) for LACC following CRT. Radiomics features were extracted from pre-treatment MR T2WI in 105 LACC patients. Following pre-feature selection and a step forward feature selection method, an optimal feature set was determined with a Cox proportional hazard (CPH) model. The PFS predictions were generated through a radiomics-clinical combined model utilized five repeated nested 5-fold cross-validation (5-fold CV). Disease progression risk was stratified into high- and low-risk groups based on the predicted PFS and assessed by Kaplan-Meier analysis. The radiomics texture feature extracted from MR T2WI significantly predict PFS in LACC after CRT. In comparison with the model using clinical variables alone, the radiomics-clinical combined model achieves significantly improved performance in testing patient cohort, achieving higher C-index (0.748 vs 0.655) and area under the curve (0.798 vs 0.660 for 2-year PFS). Meanwhile, the proposed method significantly differentiated the high- and low-risk patients groups for disease progression (P < 0.001). An MR T2WI-based radiomics and clinical combined model provided improved prognostic capabilities in predicting the PFS for LACC patients treated with CRT, outperforming a model using clinical variables alone. The incorporation of MR T2WI-based radiomics is promising in assisting in personalized management in LACC, indicating the potential of MR T2WI radiomics as imaging biomarker. •An MR T2WI based predictive model was able to predict progression-free survival for LACC after chemoradiotherapy.•Combining radiomics and clinical features improved progression-free survival prediction over using clinical variables alone.•The study outcomes support the role of MR T2WI-based radiomics as a potential imaging biomarker.
doi_str_mv 10.1016/j.clon.2024.103702
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3147972948</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0936655524005016</els_id><sourcerecordid>3147972948</sourcerecordid><originalsourceid>FETCH-LOGICAL-c237t-39cd7980b06dceaa23a28dadd7efcdcee212fa3ad03f9aecfb8b99f0d6f16b0a3</originalsourceid><addsrcrecordid>eNp9kE9rGzEQxUVpaJykX6CHomMv6-jPencFvZilaQIuDWlDj2JWGtUyu5YrrQ3Op48WJz3mMmLevPdAP0I-cTbnjFfXm7npw3YumCizIGsm3pEZL6UshGr4ezJjSlZFtVgszslFShvGmGga9YGcS1WzipdiRp7uY_gbMSUftsVNRKS_9vHgD9DT-4jWmzEfqAuRroKBvj_SpT3A1qClLWZj1mg77ZEu3Zhnu8YhRLA-jGuMsDvSP35c0x8Pd0UHKcceptvgTboiZw76hB9f3kvyePPtd3tbrH5-v2uXq8IIWY-FVMbWqmEdq6xBACFBNBasrdGZrKDgwoEEy6RTgMZ1TaeUY7ZyvOoYyEvy5dS7i-HfHtOoB58M9j1sMeyTlrysVS1U2WSrOFlNDClFdHoX_QDxqDnTE3O90RNzPTHXJ-Y59Pmlf98NaP9HXiFnw9eTAfMvDx6jTsbjxNBHNKO2wb_V_wzU9JXj</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3147972948</pqid></control><display><type>article</type><title>Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Tang, S. ; Yen, A. ; Wang, K. ; Albuquerque, K. ; Wang, J.</creator><creatorcontrib>Tang, S. ; Yen, A. ; Wang, K. ; Albuquerque, K. ; Wang, J.</creatorcontrib><description>A significant proportion of locally advanced cervical cancer (LACC) patients experience disease progression post chemoradiotherapy (CRT). Currently existing clinical variables are suboptimal predictors of treatment response. This study reported a radiomics-based model leveraging information extracted from magnetic resonance (MR) T2-weighted image (T2WI) to predict the progression-free survival (PFS) for LACC following CRT. Radiomics features were extracted from pre-treatment MR T2WI in 105 LACC patients. Following pre-feature selection and a step forward feature selection method, an optimal feature set was determined with a Cox proportional hazard (CPH) model. The PFS predictions were generated through a radiomics-clinical combined model utilized five repeated nested 5-fold cross-validation (5-fold CV). Disease progression risk was stratified into high- and low-risk groups based on the predicted PFS and assessed by Kaplan-Meier analysis. The radiomics texture feature extracted from MR T2WI significantly predict PFS in LACC after CRT. In comparison with the model using clinical variables alone, the radiomics-clinical combined model achieves significantly improved performance in testing patient cohort, achieving higher C-index (0.748 vs 0.655) and area under the curve (0.798 vs 0.660 for 2-year PFS). Meanwhile, the proposed method significantly differentiated the high- and low-risk patients groups for disease progression (P &lt; 0.001). An MR T2WI-based radiomics and clinical combined model provided improved prognostic capabilities in predicting the PFS for LACC patients treated with CRT, outperforming a model using clinical variables alone. The incorporation of MR T2WI-based radiomics is promising in assisting in personalized management in LACC, indicating the potential of MR T2WI radiomics as imaging biomarker. •An MR T2WI based predictive model was able to predict progression-free survival for LACC after chemoradiotherapy.•Combining radiomics and clinical features improved progression-free survival prediction over using clinical variables alone.•The study outcomes support the role of MR T2WI-based radiomics as a potential imaging biomarker.</description><identifier>ISSN: 0936-6555</identifier><identifier>ISSN: 1433-2981</identifier><identifier>EISSN: 1433-2981</identifier><identifier>DOI: 10.1016/j.clon.2024.103702</identifier><identifier>PMID: 39706142</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Locally advanced cervical cancer ; MR T2-weighted imaging ; progression-free survival prediction ; radiomics</subject><ispartof>Clinical oncology (Royal College of Radiologists (Great Britain)), 2025-02, Vol.38, p.103702, Article 103702</ispartof><rights>2024 The Royal College of Radiologists</rights><rights>Copyright © 2024 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c237t-39cd7980b06dceaa23a28dadd7efcdcee212fa3ad03f9aecfb8b99f0d6f16b0a3</cites><orcidid>0000-0003-2155-1445 ; 0000-0002-1115-6479 ; 0000-0002-8323-8617</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0936655524005016$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65534</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39706142$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tang, S.</creatorcontrib><creatorcontrib>Yen, A.</creatorcontrib><creatorcontrib>Wang, K.</creatorcontrib><creatorcontrib>Albuquerque, K.</creatorcontrib><creatorcontrib>Wang, J.</creatorcontrib><title>Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics</title><title>Clinical oncology (Royal College of Radiologists (Great Britain))</title><addtitle>Clin Oncol (R Coll Radiol)</addtitle><description>A significant proportion of locally advanced cervical cancer (LACC) patients experience disease progression post chemoradiotherapy (CRT). Currently existing clinical variables are suboptimal predictors of treatment response. This study reported a radiomics-based model leveraging information extracted from magnetic resonance (MR) T2-weighted image (T2WI) to predict the progression-free survival (PFS) for LACC following CRT. Radiomics features were extracted from pre-treatment MR T2WI in 105 LACC patients. Following pre-feature selection and a step forward feature selection method, an optimal feature set was determined with a Cox proportional hazard (CPH) model. The PFS predictions were generated through a radiomics-clinical combined model utilized five repeated nested 5-fold cross-validation (5-fold CV). Disease progression risk was stratified into high- and low-risk groups based on the predicted PFS and assessed by Kaplan-Meier analysis. The radiomics texture feature extracted from MR T2WI significantly predict PFS in LACC after CRT. In comparison with the model using clinical variables alone, the radiomics-clinical combined model achieves significantly improved performance in testing patient cohort, achieving higher C-index (0.748 vs 0.655) and area under the curve (0.798 vs 0.660 for 2-year PFS). Meanwhile, the proposed method significantly differentiated the high- and low-risk patients groups for disease progression (P &lt; 0.001). An MR T2WI-based radiomics and clinical combined model provided improved prognostic capabilities in predicting the PFS for LACC patients treated with CRT, outperforming a model using clinical variables alone. The incorporation of MR T2WI-based radiomics is promising in assisting in personalized management in LACC, indicating the potential of MR T2WI radiomics as imaging biomarker. •An MR T2WI based predictive model was able to predict progression-free survival for LACC after chemoradiotherapy.•Combining radiomics and clinical features improved progression-free survival prediction over using clinical variables alone.•The study outcomes support the role of MR T2WI-based radiomics as a potential imaging biomarker.</description><subject>Locally advanced cervical cancer</subject><subject>MR T2-weighted imaging</subject><subject>progression-free survival prediction</subject><subject>radiomics</subject><issn>0936-6555</issn><issn>1433-2981</issn><issn>1433-2981</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2025</creationdate><recordtype>article</recordtype><recordid>eNp9kE9rGzEQxUVpaJykX6CHomMv6-jPencFvZilaQIuDWlDj2JWGtUyu5YrrQ3Op48WJz3mMmLevPdAP0I-cTbnjFfXm7npw3YumCizIGsm3pEZL6UshGr4ezJjSlZFtVgszslFShvGmGga9YGcS1WzipdiRp7uY_gbMSUftsVNRKS_9vHgD9DT-4jWmzEfqAuRroKBvj_SpT3A1qClLWZj1mg77ZEu3Zhnu8YhRLA-jGuMsDvSP35c0x8Pd0UHKcceptvgTboiZw76hB9f3kvyePPtd3tbrH5-v2uXq8IIWY-FVMbWqmEdq6xBACFBNBasrdGZrKDgwoEEy6RTgMZ1TaeUY7ZyvOoYyEvy5dS7i-HfHtOoB58M9j1sMeyTlrysVS1U2WSrOFlNDClFdHoX_QDxqDnTE3O90RNzPTHXJ-Y59Pmlf98NaP9HXiFnw9eTAfMvDx6jTsbjxNBHNKO2wb_V_wzU9JXj</recordid><startdate>20250201</startdate><enddate>20250201</enddate><creator>Tang, S.</creator><creator>Yen, A.</creator><creator>Wang, K.</creator><creator>Albuquerque, K.</creator><creator>Wang, J.</creator><general>Elsevier Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-2155-1445</orcidid><orcidid>https://orcid.org/0000-0002-1115-6479</orcidid><orcidid>https://orcid.org/0000-0002-8323-8617</orcidid></search><sort><creationdate>20250201</creationdate><title>Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics</title><author>Tang, S. ; Yen, A. ; Wang, K. ; Albuquerque, K. ; Wang, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c237t-39cd7980b06dceaa23a28dadd7efcdcee212fa3ad03f9aecfb8b99f0d6f16b0a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2025</creationdate><topic>Locally advanced cervical cancer</topic><topic>MR T2-weighted imaging</topic><topic>progression-free survival prediction</topic><topic>radiomics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tang, S.</creatorcontrib><creatorcontrib>Yen, A.</creatorcontrib><creatorcontrib>Wang, K.</creatorcontrib><creatorcontrib>Albuquerque, K.</creatorcontrib><creatorcontrib>Wang, J.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Clinical oncology (Royal College of Radiologists (Great Britain))</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tang, S.</au><au>Yen, A.</au><au>Wang, K.</au><au>Albuquerque, K.</au><au>Wang, J.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics</atitle><jtitle>Clinical oncology (Royal College of Radiologists (Great Britain))</jtitle><addtitle>Clin Oncol (R Coll Radiol)</addtitle><date>2025-02-01</date><risdate>2025</risdate><volume>38</volume><spage>103702</spage><pages>103702-</pages><artnum>103702</artnum><issn>0936-6555</issn><issn>1433-2981</issn><eissn>1433-2981</eissn><abstract>A significant proportion of locally advanced cervical cancer (LACC) patients experience disease progression post chemoradiotherapy (CRT). Currently existing clinical variables are suboptimal predictors of treatment response. This study reported a radiomics-based model leveraging information extracted from magnetic resonance (MR) T2-weighted image (T2WI) to predict the progression-free survival (PFS) for LACC following CRT. Radiomics features were extracted from pre-treatment MR T2WI in 105 LACC patients. Following pre-feature selection and a step forward feature selection method, an optimal feature set was determined with a Cox proportional hazard (CPH) model. The PFS predictions were generated through a radiomics-clinical combined model utilized five repeated nested 5-fold cross-validation (5-fold CV). Disease progression risk was stratified into high- and low-risk groups based on the predicted PFS and assessed by Kaplan-Meier analysis. The radiomics texture feature extracted from MR T2WI significantly predict PFS in LACC after CRT. In comparison with the model using clinical variables alone, the radiomics-clinical combined model achieves significantly improved performance in testing patient cohort, achieving higher C-index (0.748 vs 0.655) and area under the curve (0.798 vs 0.660 for 2-year PFS). Meanwhile, the proposed method significantly differentiated the high- and low-risk patients groups for disease progression (P &lt; 0.001). An MR T2WI-based radiomics and clinical combined model provided improved prognostic capabilities in predicting the PFS for LACC patients treated with CRT, outperforming a model using clinical variables alone. The incorporation of MR T2WI-based radiomics is promising in assisting in personalized management in LACC, indicating the potential of MR T2WI radiomics as imaging biomarker. •An MR T2WI based predictive model was able to predict progression-free survival for LACC after chemoradiotherapy.•Combining radiomics and clinical features improved progression-free survival prediction over using clinical variables alone.•The study outcomes support the role of MR T2WI-based radiomics as a potential imaging biomarker.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>39706142</pmid><doi>10.1016/j.clon.2024.103702</doi><orcidid>https://orcid.org/0000-0003-2155-1445</orcidid><orcidid>https://orcid.org/0000-0002-1115-6479</orcidid><orcidid>https://orcid.org/0000-0002-8323-8617</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0936-6555
ispartof Clinical oncology (Royal College of Radiologists (Great Britain)), 2025-02, Vol.38, p.103702, Article 103702
issn 0936-6555
1433-2981
1433-2981
language eng
recordid cdi_proquest_miscellaneous_3147972948
source Elsevier ScienceDirect Journals Complete
subjects Locally advanced cervical cancer
MR T2-weighted imaging
progression-free survival prediction
radiomics
title Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based Radiomics
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T10%3A53%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Progression-Free%20Survival%20Prediction%20for%20Locally%20Advanced%20Cervical%20Cancer%20After%20Chemoradiotherapy%20With%20MRI-based%20Radiomics&rft.jtitle=Clinical%20oncology%20(Royal%20College%20of%20Radiologists%20(Great%20Britain))&rft.au=Tang,%20S.&rft.date=2025-02-01&rft.volume=38&rft.spage=103702&rft.pages=103702-&rft.artnum=103702&rft.issn=0936-6555&rft.eissn=1433-2981&rft_id=info:doi/10.1016/j.clon.2024.103702&rft_dat=%3Cproquest_cross%3E3147972948%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3147972948&rft_id=info:pmid/39706142&rft_els_id=S0936655524005016&rfr_iscdi=true