Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients

Abstract Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors’ radiological phenotype with machine-learning to improve predict...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Amandine Crombé, Michèle Kind, David Fadli, François Le Loarer, Antoine Italiano, Xavier Buy, Olivier Saut
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
R
Q
Acceso en línea:https://doaj.org/article/171eb74794744b88a09d9e582358e5b0
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:171eb74794744b88a09d9e582358e5b0
record_format dspace
spelling oai:doaj.org-article:171eb74794744b88a09d9e582358e5b02021-12-02T18:48:01ZIntensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients10.1038/s41598-020-72535-02045-2322https://doaj.org/article/171eb74794744b88a09d9e582358e5b02020-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-72535-0https://doaj.org/toc/2045-2322Abstract Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors’ radiological phenotype with machine-learning to improve predictive models, such as metastastic-relapse-free survival (MFS) for sarcoma patients. We post-processed the initial T2-weighted-imaging of 70 sarcoma patients by using 5 IHTs and extracting 45 radiomics features (RFs), namely: classical standardization (IHTstd), standardization per adipose tissue SIs (IHTfat), histogram-matching with a patient histogram (IHTHM.1), with the average histogram of the population (IHTHM.All) and plus ComBat method (IHTHM.All.C), which provided 5 radiomics datasets in addition to the original radiomics dataset without IHT (No-IHT). We found that using IHTs significantly influenced all RFs values (p-values: < 0.0001–0.02). Unsupervised clustering performed on each radiomics dataset showed that only clusters from the No-IHT, IHTstd, IHTHM.All, and IHTHM.All.C datasets significantly correlated with MFS in multivariate Cox models (p = 0.02, 0.007, 0.004 and 0.02, respectively). We built radiomics-based supervised models to predict metastatic relapse at 2-years with a training set of 50 patients. The models performances varied markedly depending on the IHT in the validation set (range of AUROC from 0.688 with IHTstd to 0.823 with IHTHM.1). Hence, the use of intensity harmonization and the related technique should be carefully detailed in radiomics post-processing pipelines as it can profoundly affect the reproducibility of analyses.Amandine CrombéMichèle KindDavid FadliFrançois Le LoarerAntoine ItalianoXavier BuyOlivier SautNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Amandine Crombé
Michèle Kind
David Fadli
François Le Loarer
Antoine Italiano
Xavier Buy
Olivier Saut
Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
description Abstract Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors’ radiological phenotype with machine-learning to improve predictive models, such as metastastic-relapse-free survival (MFS) for sarcoma patients. We post-processed the initial T2-weighted-imaging of 70 sarcoma patients by using 5 IHTs and extracting 45 radiomics features (RFs), namely: classical standardization (IHTstd), standardization per adipose tissue SIs (IHTfat), histogram-matching with a patient histogram (IHTHM.1), with the average histogram of the population (IHTHM.All) and plus ComBat method (IHTHM.All.C), which provided 5 radiomics datasets in addition to the original radiomics dataset without IHT (No-IHT). We found that using IHTs significantly influenced all RFs values (p-values: < 0.0001–0.02). Unsupervised clustering performed on each radiomics dataset showed that only clusters from the No-IHT, IHTstd, IHTHM.All, and IHTHM.All.C datasets significantly correlated with MFS in multivariate Cox models (p = 0.02, 0.007, 0.004 and 0.02, respectively). We built radiomics-based supervised models to predict metastatic relapse at 2-years with a training set of 50 patients. The models performances varied markedly depending on the IHT in the validation set (range of AUROC from 0.688 with IHTstd to 0.823 with IHTHM.1). Hence, the use of intensity harmonization and the related technique should be carefully detailed in radiomics post-processing pipelines as it can profoundly affect the reproducibility of analyses.
format article
author Amandine Crombé
Michèle Kind
David Fadli
François Le Loarer
Antoine Italiano
Xavier Buy
Olivier Saut
author_facet Amandine Crombé
Michèle Kind
David Fadli
François Le Loarer
Antoine Italiano
Xavier Buy
Olivier Saut
author_sort Amandine Crombé
title Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
title_short Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
title_full Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
title_fullStr Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
title_full_unstemmed Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
title_sort intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/171eb74794744b88a09d9e582358e5b0
work_keys_str_mv AT amandinecrombe intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT michelekind intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT davidfadli intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT francoisleloarer intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT antoineitaliano intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT xavierbuy intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
AT oliviersaut intensityharmonizationtechniquesinfluenceradiomicsfeaturesandradiomicsbasedpredictionsinsarcomapatients
_version_ 1718377607284654080