External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer
Adjuvant radiotherapy after prostatectomy was recently challenged by early salvage radiotherapy, which highlighted the need for biomarkers to improve risk stratification. Therefore, we developed an MRI ADC map-derived radiomics model to predict biochemical recurrence (BCR) and BCR-free survival (bRF...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/12/4/814 |
id |
doaj-10f3b4febf884821b3f6aa3ce745c6b7 |
---|---|
record_format |
Article |
spelling |
doaj-10f3b4febf884821b3f6aa3ce745c6b72020-11-25T02:05:33ZengMDPI AGCancers2072-66942020-03-011281481410.3390/cancers12040814External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate CancerVincent Bourbonne0Georges Fournier1Martin Vallières2François Lucia3Laurent Doucet4Valentin Tissot5Gilles Cuvelier6Stephane Hue7Henri Le Penn Du8Luc Perdriel9Nicolas Bertrand10Frederic Staroz11Dimitris Visvikis12Olivier Pradier13Mathieu Hatt14Ulrike Schick15Department of Radiation Oncology, CHRU Brest, 29200 Brest, FranceUrology Department, CHRU Brest, 29200 Brest, FranceLaTIM, INSERM, UMR 1101, CHRU Brest, 29200 Brest, FranceDepartment of Radiation Oncology, CHRU Brest, 29200 Brest, FranceAnatomopathology Department, CHRU Brest, 29200 Brest, FranceRadiology Department, CHRU Brest, 29200 Brest, FranceUrology Department, Cornouaille Hospital, 29000 Quimper, FranceRadiology Department, Cornouaille Hospital, 29000 Quimper, FranceRadiology Department, Keraudren Clinique, 29000 Brest, FranceRadiology Department, Clinique St Michel, 29000 Quimper, FranceUrology Department, Clinique St Michel, 29000 Quimper, FranceAnatomopathology Department, Ouest Pathologie, 29000 Quimper, FranceLaTIM, INSERM, UMR 1101, CHRU Brest, 29200 Brest, FranceDepartment of Radiation Oncology, CHRU Brest, 29200 Brest, FranceLaTIM, INSERM, UMR 1101, CHRU Brest, 29200 Brest, FranceDepartment of Radiation Oncology, CHRU Brest, 29200 Brest, FranceAdjuvant radiotherapy after prostatectomy was recently challenged by early salvage radiotherapy, which highlighted the need for biomarkers to improve risk stratification. Therefore, we developed an MRI ADC map-derived radiomics model to predict biochemical recurrence (BCR) and BCR-free survival (bRFS) after surgery. Our goal in this work was to externally validate this radiomics-based prediction model. Experimental Design: A total of 195 patients with a high recurrence risk of prostate cancer (pT3-4 and/or R1 and/or Gleason’s score > 7) were retrospectively included in two institutions. Patients with postoperative PSA (Prostate Specific Antigen) > 0.04 ng/mL or lymph node involvement were excluded. Radiomics features were extracted from T2 and ADC delineated tumors. A total of 107 patients from Institution 1 were used to retrain the previously published model. The retrained model was then applied to 88 patients from Institution 2 for external validation. BCR predictions were evaluated using AUC (Area Under the Curve), accuracy, and bRFS using Kaplan–Meier curves. Results: With a median follow-up of 46.3 months, 52/195 patients experienced BCR. In the retraining cohort, the clinical prediction model (combining the number of risk factors and postoperative PSA) demonstrated moderate predictive power (accuracy of 63%). The radiomics model (ADC-based SZE<sub>GLSZM)</sub> predicted BCR with an accuracy of 78% and allowed for significant stratification of patients for bRFS (<i>p</i> < 0.0001). In Institution 2, this radiomics model remained predictive of BCR (accuracy of 0.76%) contrary to the clinical model (accuracy of 0.56%). Conclusions: The recently developed MRI ADC map-based radiomics model was validated in terms of its predictive accuracy of BCR and bRFS after prostatectomy in an external cohort.https://www.mdpi.com/2072-6694/12/4/814magnetic resonance imagingprostatic neoplasmsradiomicsmachine learningtreatment failure |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vincent Bourbonne Georges Fournier Martin Vallières François Lucia Laurent Doucet Valentin Tissot Gilles Cuvelier Stephane Hue Henri Le Penn Du Luc Perdriel Nicolas Bertrand Frederic Staroz Dimitris Visvikis Olivier Pradier Mathieu Hatt Ulrike Schick |
spellingShingle |
Vincent Bourbonne Georges Fournier Martin Vallières François Lucia Laurent Doucet Valentin Tissot Gilles Cuvelier Stephane Hue Henri Le Penn Du Luc Perdriel Nicolas Bertrand Frederic Staroz Dimitris Visvikis Olivier Pradier Mathieu Hatt Ulrike Schick External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer Cancers magnetic resonance imaging prostatic neoplasms radiomics machine learning treatment failure |
author_facet |
Vincent Bourbonne Georges Fournier Martin Vallières François Lucia Laurent Doucet Valentin Tissot Gilles Cuvelier Stephane Hue Henri Le Penn Du Luc Perdriel Nicolas Bertrand Frederic Staroz Dimitris Visvikis Olivier Pradier Mathieu Hatt Ulrike Schick |
author_sort |
Vincent Bourbonne |
title |
External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer |
title_short |
External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer |
title_full |
External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer |
title_fullStr |
External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer |
title_full_unstemmed |
External Validation of an MRI-Derived Radiomics Model to Predict Biochemical Recurrence after Surgery for High-Risk Prostate Cancer |
title_sort |
external validation of an mri-derived radiomics model to predict biochemical recurrence after surgery for high-risk prostate cancer |
publisher |
MDPI AG |
series |
Cancers |
issn |
2072-6694 |
publishDate |
2020-03-01 |
description |
Adjuvant radiotherapy after prostatectomy was recently challenged by early salvage radiotherapy, which highlighted the need for biomarkers to improve risk stratification. Therefore, we developed an MRI ADC map-derived radiomics model to predict biochemical recurrence (BCR) and BCR-free survival (bRFS) after surgery. Our goal in this work was to externally validate this radiomics-based prediction model. Experimental Design: A total of 195 patients with a high recurrence risk of prostate cancer (pT3-4 and/or R1 and/or Gleason’s score > 7) were retrospectively included in two institutions. Patients with postoperative PSA (Prostate Specific Antigen) > 0.04 ng/mL or lymph node involvement were excluded. Radiomics features were extracted from T2 and ADC delineated tumors. A total of 107 patients from Institution 1 were used to retrain the previously published model. The retrained model was then applied to 88 patients from Institution 2 for external validation. BCR predictions were evaluated using AUC (Area Under the Curve), accuracy, and bRFS using Kaplan–Meier curves. Results: With a median follow-up of 46.3 months, 52/195 patients experienced BCR. In the retraining cohort, the clinical prediction model (combining the number of risk factors and postoperative PSA) demonstrated moderate predictive power (accuracy of 63%). The radiomics model (ADC-based SZE<sub>GLSZM)</sub> predicted BCR with an accuracy of 78% and allowed for significant stratification of patients for bRFS (<i>p</i> < 0.0001). In Institution 2, this radiomics model remained predictive of BCR (accuracy of 0.76%) contrary to the clinical model (accuracy of 0.56%). Conclusions: The recently developed MRI ADC map-based radiomics model was validated in terms of its predictive accuracy of BCR and bRFS after prostatectomy in an external cohort. |
topic |
magnetic resonance imaging prostatic neoplasms radiomics machine learning treatment failure |
url |
https://www.mdpi.com/2072-6694/12/4/814 |
work_keys_str_mv |
AT vincentbourbonne externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT georgesfournier externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT martinvallieres externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT francoislucia externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT laurentdoucet externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT valentintissot externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT gillescuvelier externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT stephanehue externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT henrilepenndu externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT lucperdriel externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT nicolasbertrand externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT fredericstaroz externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT dimitrisvisvikis externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT olivierpradier externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT mathieuhatt externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer AT ulrikeschick externalvalidationofanmriderivedradiomicsmodeltopredictbiochemicalrecurrenceaftersurgeryforhighriskprostatecancer |
_version_ |
1724937596415508480 |