Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients

Significant advances in lymph node involvement (LNI) risk modeling in prostate cancer (PCa) have been achieved with the addition of visual interpretation of magnetic resonance imaging (MRI) data, but it is likely that quantitative analysis could further improve prediction models. In this study, we a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Vincent Bourbonne, Vincent Jaouen, Truong An Nguyen, Valentin Tissot, Laurent Doucet, Mathieu Hatt, Dimitris Visvikis, Olivier Pradier, Antoine Valéri, Georges Fournier, Ulrike Schick
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	lymph node involvement prostate cancer prediction radiomics MRI Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/16e452384f4c44e9aed8e538056cc96b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:16e452384f4c44e9aed8e538056cc96b
record_format	dspace
spelling	oai:doaj.org-article:16e452384f4c44e9aed8e538056cc96b2021-11-25T17:02:31ZDevelopment of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients10.3390/cancers132256722072-6694https://doaj.org/article/16e452384f4c44e9aed8e538056cc96b2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-6694/13/22/5672https://doaj.org/toc/2072-6694Significant advances in lymph node involvement (LNI) risk modeling in prostate cancer (PCa) have been achieved with the addition of visual interpretation of magnetic resonance imaging (MRI) data, but it is likely that quantitative analysis could further improve prediction models. In this study, we aimed to develop and internally validate a novel LNI risk prediction model based on radiomic features extracted from preoperative multimodal MRI. All patients who underwent a preoperative MRI and radical prostatectomy with extensive lymph node dissection were retrospectively included in a single institution. Patients were randomly divided into the training (60%) and testing (40%) sets. Radiomic features were extracted from the index tumor volumes, delineated on the apparent diffusion coefficient corrected map and the T2 sequences. A ComBat harmonization method was applied to account for inter-site heterogeneity. A prediction model was trained using a neural network approach (Multilayer Perceptron Network, SPSS v24.0©) combining clinical, radiomic and all features. It was then evaluated on the testing set and compared to the current available models using the Receiver Operative Characteristics and the C-Index. Two hundred and eighty patients were included, with a median age of 65.2 y (45.3–79.6), a mean PSA level of 9.5 ng/mL (1.04–63.0) and 79.6% of ISUP ≥ 2 tumors. LNI occurred in 51 patients (18.2%), with a median number of extracted nodes of 15 (10–19). In the testing set, with their respective cutoffs applied, the Partin, Roach, Yale, MSKCC, Briganti 2012 and 2017 models resulted in a C-Index of 0.71, 0.66, 0.55, 0.67, 0.65 and 0.73, respectively, while our proposed combined model resulted in a C-Index of 0.89 in the testing set. Radiomic features extracted from the preoperative MRI scans and combined with clinical features through a neural network seem to provide added predictive performance compared to state of the art models regarding LNI risk prediction in PCa.Vincent BourbonneVincent JaouenTruong An NguyenValentin TissotLaurent DoucetMathieu HattDimitris VisvikisOlivier PradierAntoine ValériGeorges FournierUlrike SchickMDPI AGarticlelymph node involvementprostate cancerpredictionradiomicsMRINeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENCancers, Vol 13, Iss 5672, p 5672 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	lymph node involvement prostate cancer prediction radiomics MRI Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	lymph node involvement prostate cancer prediction radiomics MRI Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Vincent Bourbonne Vincent Jaouen Truong An Nguyen Valentin Tissot Laurent Doucet Mathieu Hatt Dimitris Visvikis Olivier Pradier Antoine Valéri Georges Fournier Ulrike Schick Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
description	Significant advances in lymph node involvement (LNI) risk modeling in prostate cancer (PCa) have been achieved with the addition of visual interpretation of magnetic resonance imaging (MRI) data, but it is likely that quantitative analysis could further improve prediction models. In this study, we aimed to develop and internally validate a novel LNI risk prediction model based on radiomic features extracted from preoperative multimodal MRI. All patients who underwent a preoperative MRI and radical prostatectomy with extensive lymph node dissection were retrospectively included in a single institution. Patients were randomly divided into the training (60%) and testing (40%) sets. Radiomic features were extracted from the index tumor volumes, delineated on the apparent diffusion coefficient corrected map and the T2 sequences. A ComBat harmonization method was applied to account for inter-site heterogeneity. A prediction model was trained using a neural network approach (Multilayer Perceptron Network, SPSS v24.0©) combining clinical, radiomic and all features. It was then evaluated on the testing set and compared to the current available models using the Receiver Operative Characteristics and the C-Index. Two hundred and eighty patients were included, with a median age of 65.2 y (45.3–79.6), a mean PSA level of 9.5 ng/mL (1.04–63.0) and 79.6% of ISUP ≥ 2 tumors. LNI occurred in 51 patients (18.2%), with a median number of extracted nodes of 15 (10–19). In the testing set, with their respective cutoffs applied, the Partin, Roach, Yale, MSKCC, Briganti 2012 and 2017 models resulted in a C-Index of 0.71, 0.66, 0.55, 0.67, 0.65 and 0.73, respectively, while our proposed combined model resulted in a C-Index of 0.89 in the testing set. Radiomic features extracted from the preoperative MRI scans and combined with clinical features through a neural network seem to provide added predictive performance compared to state of the art models regarding LNI risk prediction in PCa.
format	article
author	Vincent Bourbonne Vincent Jaouen Truong An Nguyen Valentin Tissot Laurent Doucet Mathieu Hatt Dimitris Visvikis Olivier Pradier Antoine Valéri Georges Fournier Ulrike Schick
author_facet	Vincent Bourbonne Vincent Jaouen Truong An Nguyen Valentin Tissot Laurent Doucet Mathieu Hatt Dimitris Visvikis Olivier Pradier Antoine Valéri Georges Fournier Ulrike Schick
author_sort	Vincent Bourbonne
title	Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
title_short	Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
title_full	Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
title_fullStr	Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
title_full_unstemmed	Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients
title_sort	development of a radiomic-based model predicting lymph node involvement in prostate cancer patients
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/16e452384f4c44e9aed8e538056cc96b
work_keys_str_mv	AT vincentbourbonne developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT vincentjaouen developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT truongannguyen developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT valentintissot developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT laurentdoucet developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT mathieuhatt developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT dimitrisvisvikis developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT olivierpradier developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT antoinevaleri developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT georgesfournier developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients AT ulrikeschick developmentofaradiomicbasedmodelpredictinglymphnodeinvolvementinprostatecancerpatients
_version_	1718412760292786176

Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients

Ejemplares similares