Cargando…

A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets

PURPOSE: To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reco...

Descripción completa

Detalles Bibliográficos
Autores principales: Da-ano, Ronrick, Lucia, François, Masson, Ingrid, Abgral, Ronan, Alfieri, Joanne, Rousseau, Caroline, Mervoyer, Augustin, Reinhold, Caroline, Pradier, Olivier, Schick, Ulrike, Visvikis, Dimitris, Hatt, Mathieu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8248970/
https://www.ncbi.nlm.nih.gov/pubmed/34197503
http://dx.doi.org/10.1371/journal.pone.0253653
_version_ 1783716821076017152
author Da-ano, Ronrick
Lucia, François
Masson, Ingrid
Abgral, Ronan
Alfieri, Joanne
Rousseau, Caroline
Mervoyer, Augustin
Reinhold, Caroline
Pradier, Olivier
Schick, Ulrike
Visvikis, Dimitris
Hatt, Mathieu
author_facet Da-ano, Ronrick
Lucia, François
Masson, Ingrid
Abgral, Ronan
Alfieri, Joanne
Rousseau, Caroline
Mervoyer, Augustin
Reinhold, Caroline
Pradier, Olivier
Schick, Ulrike
Visvikis, Dimitris
Hatt, Mathieu
author_sort Da-ano, Ronrick
collection PubMed
description PURPOSE: To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the “center-effect”. The goal of the present work was to integrate a transfer learning (TL) technique within ComBat—and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)–to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center. MATERIAL AND METHODS: The proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines. RESULTS: The proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available. CONCLUSION: The proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data.
format Online
Article
Text
id pubmed-8248970
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-82489702021-07-09 A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets Da-ano, Ronrick Lucia, François Masson, Ingrid Abgral, Ronan Alfieri, Joanne Rousseau, Caroline Mervoyer, Augustin Reinhold, Caroline Pradier, Olivier Schick, Ulrike Visvikis, Dimitris Hatt, Mathieu PLoS One Research Article PURPOSE: To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the “center-effect”. The goal of the present work was to integrate a transfer learning (TL) technique within ComBat—and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)–to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center. MATERIAL AND METHODS: The proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines. RESULTS: The proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available. CONCLUSION: The proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data. Public Library of Science 2021-07-01 /pmc/articles/PMC8248970/ /pubmed/34197503 http://dx.doi.org/10.1371/journal.pone.0253653 Text en © 2021 Da-ano et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Da-ano, Ronrick
Lucia, François
Masson, Ingrid
Abgral, Ronan
Alfieri, Joanne
Rousseau, Caroline
Mervoyer, Augustin
Reinhold, Caroline
Pradier, Olivier
Schick, Ulrike
Visvikis, Dimitris
Hatt, Mathieu
A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title_full A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title_fullStr A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title_full_unstemmed A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title_short A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets
title_sort transfer learning approach to facilitate combat-based harmonization of multicentre radiomic features in new datasets
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8248970/
https://www.ncbi.nlm.nih.gov/pubmed/34197503
http://dx.doi.org/10.1371/journal.pone.0253653
work_keys_str_mv AT daanoronrick atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT luciafrancois atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT massoningrid atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT abgralronan atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT alfierijoanne atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT rousseaucaroline atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT mervoyeraugustin atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT reinholdcaroline atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT pradierolivier atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT schickulrike atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT visvikisdimitris atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT hattmathieu atransferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT daanoronrick transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT luciafrancois transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT massoningrid transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT abgralronan transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT alfierijoanne transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT rousseaucaroline transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT mervoyeraugustin transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT reinholdcaroline transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT pradierolivier transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT schickulrike transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT visvikisdimitris transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets
AT hattmathieu transferlearningapproachtofacilitatecombatbasedharmonizationofmulticentreradiomicfeaturesinnewdatasets