Development and validation of an MRI-based model to predict response to chemoradiotherapy for rectal cancer

Philippe Bulens; Alice Couwenberg; Karin Haustermans; Annelies Debucquoy; Vincent Vandecaveye; Marielle Philippens; Mu Zhou; Olivier Gevaert; Martijn Intven

doi:10.1016/j.radonc.2018.01.008

Development and validation of an MRI-based model to predict response to chemoradiotherapy for rectal cancer

Philippe Bulens, Alice Couwenberg, Karin Haustermans, Annelies Debucquoy, Vincent Vandecaveye, Marielle Philippens, Mu Zhou, Olivier Gevaert, Martijn Intven

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

BACKGROUND AND PURPOSE: To safely implement organ preserving treatment strategies for patients with rectal cancer, well-considered selection of patients with favourable response is needed. In this study, we develop and validate an MRI-based response predicting model.

METHODS: A multivariate model using T2-volumetric and DWI parameters before and 6 weeks after chemoradiation (CRT) was developed using a cohort of 85 rectal cancer patients and validated in an external cohort of 55 patients that underwent preoperative CRT.

RESULTS: Twenty-two patients (26%) achieved ypT0-1N0 response in the development cohort versus 13 patients (24%) in the validation cohort. Two T2-volumetric parameters (ΔVolume% and Sphere_post) and two DWI parameters (ADC_avg_post and ADCratio_avg) were retained in a model predicting (near-)complete response (ypT0-1N0). In the development cohort, this model had a good predictive performance (AUC = 0.89; 95% CI 0.80-0.98). Validation of the model in an external cohort resulted in a similar performance (AUC = 0.88 95% CI 0.79-0.98).

CONCLUSION: An MRI-based prediction model of (near-)complete pathological response following CRT in rectal cancer patients, shows a high predictive performance in an external validation cohort. The clinically relevant features in the model make it an interesting tool for implementation of organ-preserving strategies in rectal cancer.

Original language	English
Pages (from-to)	437-442
Number of pages	6
Journal	Radiotherapy & Oncology
Volume	126
Issue number	3
DOIs	https://doi.org/10.1016/j.radonc.2018.01.008
Publication status	Published - Mar 2018

Keywords

Chemoradiotherapy
DWI
MRI
Rectal cancer
Response prediction

Access to Document

10.1016/j.radonc.2018.01.008

Cite this

@article{d2563d90676a4ca6a0da02d61d323945,

title = "Development and validation of an MRI-based model to predict response to chemoradiotherapy for rectal cancer",

abstract = "BACKGROUND AND PURPOSE: To safely implement organ preserving treatment strategies for patients with rectal cancer, well-considered selection of patients with favourable response is needed. In this study, we develop and validate an MRI-based response predicting model.METHODS: A multivariate model using T2-volumetric and DWI parameters before and 6 weeks after chemoradiation (CRT) was developed using a cohort of 85 rectal cancer patients and validated in an external cohort of 55 patients that underwent preoperative CRT.RESULTS: Twenty-two patients (26%) achieved ypT0-1N0 response in the development cohort versus 13 patients (24%) in the validation cohort. Two T2-volumetric parameters (ΔVolume% and Sphere_post) and two DWI parameters (ADC_avg_post and ADCratio_avg) were retained in a model predicting (near-)complete response (ypT0-1N0). In the development cohort, this model had a good predictive performance (AUC = 0.89; 95% CI 0.80-0.98). Validation of the model in an external cohort resulted in a similar performance (AUC = 0.88 95% CI 0.79-0.98).CONCLUSION: An MRI-based prediction model of (near-)complete pathological response following CRT in rectal cancer patients, shows a high predictive performance in an external validation cohort. The clinically relevant features in the model make it an interesting tool for implementation of organ-preserving strategies in rectal cancer.",

keywords = "Chemoradiotherapy, DWI, MRI, Rectal cancer, Response prediction",

author = "Philippe Bulens and Alice Couwenberg and Karin Haustermans and Annelies Debucquoy and Vincent Vandecaveye and Marielle Philippens and Mu Zhou and Olivier Gevaert and Martijn Intven",

note = "Funding Information: This work was funded by the Belgian Government Agency for Innovation by Science and Technology (IWT). Philippe Bulens is an aspirant investigator at the Research Foundation Flanders (FWO). Karin Haustermans is a senior clinical investigator at the Research Foundation Flanders (FWO). Research reported in this publication was further supported by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under Award Number R01 EB020527. Funding Information: This work was funded by the Belgian Government Agency for Innovation by Science and Technology (IWT). Philippe Bulens is an aspirant investigator at the Research Foundation Flanders (FWO). Karin Haustermans is a senior clinical investigator at the Research Foundation Flanders (FWO). Research reported in this publication was further supported by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under Award Number R01 EB020527. Publisher Copyright: {\textcopyright} 2018 Elsevier B.V.",

year = "2018",

month = mar,

doi = "10.1016/j.radonc.2018.01.008",

language = "English",

volume = "126",

pages = "437--442",

journal = "Radiotherapy & Oncology",

issn = "0167-8140",

publisher = "Elsevier Ireland Ltd",

number = "3",

}

TY - JOUR

T1 - Development and validation of an MRI-based model to predict response to chemoradiotherapy for rectal cancer

AU - Bulens, Philippe

AU - Couwenberg, Alice

AU - Haustermans, Karin

AU - Debucquoy, Annelies

AU - Vandecaveye, Vincent

AU - Philippens, Marielle

AU - Zhou, Mu

AU - Gevaert, Olivier

AU - Intven, Martijn

N1 - Funding Information: This work was funded by the Belgian Government Agency for Innovation by Science and Technology (IWT). Philippe Bulens is an aspirant investigator at the Research Foundation Flanders (FWO). Karin Haustermans is a senior clinical investigator at the Research Foundation Flanders (FWO). Research reported in this publication was further supported by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under Award Number R01 EB020527. Funding Information: This work was funded by the Belgian Government Agency for Innovation by Science and Technology (IWT). Philippe Bulens is an aspirant investigator at the Research Foundation Flanders (FWO). Karin Haustermans is a senior clinical investigator at the Research Foundation Flanders (FWO). Research reported in this publication was further supported by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under Award Number R01 EB020527. Publisher Copyright: © 2018 Elsevier B.V.

PY - 2018/3

Y1 - 2018/3

N2 - BACKGROUND AND PURPOSE: To safely implement organ preserving treatment strategies for patients with rectal cancer, well-considered selection of patients with favourable response is needed. In this study, we develop and validate an MRI-based response predicting model.METHODS: A multivariate model using T2-volumetric and DWI parameters before and 6 weeks after chemoradiation (CRT) was developed using a cohort of 85 rectal cancer patients and validated in an external cohort of 55 patients that underwent preoperative CRT.RESULTS: Twenty-two patients (26%) achieved ypT0-1N0 response in the development cohort versus 13 patients (24%) in the validation cohort. Two T2-volumetric parameters (ΔVolume% and Sphere_post) and two DWI parameters (ADC_avg_post and ADCratio_avg) were retained in a model predicting (near-)complete response (ypT0-1N0). In the development cohort, this model had a good predictive performance (AUC = 0.89; 95% CI 0.80-0.98). Validation of the model in an external cohort resulted in a similar performance (AUC = 0.88 95% CI 0.79-0.98).CONCLUSION: An MRI-based prediction model of (near-)complete pathological response following CRT in rectal cancer patients, shows a high predictive performance in an external validation cohort. The clinically relevant features in the model make it an interesting tool for implementation of organ-preserving strategies in rectal cancer.

AB - BACKGROUND AND PURPOSE: To safely implement organ preserving treatment strategies for patients with rectal cancer, well-considered selection of patients with favourable response is needed. In this study, we develop and validate an MRI-based response predicting model.METHODS: A multivariate model using T2-volumetric and DWI parameters before and 6 weeks after chemoradiation (CRT) was developed using a cohort of 85 rectal cancer patients and validated in an external cohort of 55 patients that underwent preoperative CRT.RESULTS: Twenty-two patients (26%) achieved ypT0-1N0 response in the development cohort versus 13 patients (24%) in the validation cohort. Two T2-volumetric parameters (ΔVolume% and Sphere_post) and two DWI parameters (ADC_avg_post and ADCratio_avg) were retained in a model predicting (near-)complete response (ypT0-1N0). In the development cohort, this model had a good predictive performance (AUC = 0.89; 95% CI 0.80-0.98). Validation of the model in an external cohort resulted in a similar performance (AUC = 0.88 95% CI 0.79-0.98).CONCLUSION: An MRI-based prediction model of (near-)complete pathological response following CRT in rectal cancer patients, shows a high predictive performance in an external validation cohort. The clinically relevant features in the model make it an interesting tool for implementation of organ-preserving strategies in rectal cancer.

KW - Chemoradiotherapy

KW - DWI

KW - MRI

KW - Rectal cancer

KW - Response prediction

UR - http://www.scopus.com/inward/record.url?scp=85041214374&partnerID=8YFLogxK

U2 - 10.1016/j.radonc.2018.01.008

DO - 10.1016/j.radonc.2018.01.008

M3 - Article

C2 - 29395287

SN - 0167-8140

VL - 126

SP - 437

EP - 442

JO - Radiotherapy & Oncology

JF - Radiotherapy & Oncology

IS - 3

ER -

Development and validation of an MRI-based model to predict response to chemoradiotherapy for rectal cancer

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this