Minimising multi-centre radiomics variability through image normalisation: a pilot study

Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging st...

Descripción completa

Detalles Bibliográficos
Autores: Campello, VM, Martin-Isla, C, Izquierdo, C, Guala, A, Palomares, JFR, Vilades, D, Descalzo, ML, Karakas, M, Cavus, E, Raisi-Estabragh, Z, Petersen, SE, Escalera, S, Segui, S, Lekadir, K
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
Repositorio:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
OAI Identifier:oai:iibsantpau.fundanetsuite.com:p12291
Acceso en línea:https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=12291
https://ddd.uab.cat/record/277673
Access Level:acceso abierto
Palabra clave:diagnostic imaging
human
hypertrophic cardiomyopathy
nuclear magnetic resonance imaging
pilot study
procedures
Cardiomyopathy, Hypertrophic
Humans
Magnetic Resonance Imaging
Pilot Projects
id ES_0ca09c340d1debcfbab667a805f23eb2
oai_identifier_str oai:iibsantpau.fundanetsuite.com:p12291
network_acronym_str ES
network_name_str España
repository_id_str
spelling Minimising multi-centre radiomics variability through image normalisation: a pilot studyCampello, VMMartin-Isla, CIzquierdo, CGuala, APalomares, JFRVilades, DDescalzo, MLKarakas, MCavus, ERaisi-Estabragh, ZPetersen, SEEscalera, SSegui, SLekadir, Kdiagnostic imaginghumanhypertrophic cardiomyopathynuclear magnetic resonance imagingpilot studyproceduresCardiomyopathy, HypertrophicHumansMagnetic Resonance ImagingPilot ProjectsRadiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features' variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 +/- 0.08 and 0.79 +/- 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 +/- 0.28 and 0.60 +/- 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.NATURE RESEARCH2022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=12291https://ddd.uab.cat/record/277673Scientific ReportsISSN: 20452322reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pauinstname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)Inglésinfo:eu-repo/semantics/openAccessoai:iibsantpau.fundanetsuite.com:p122912026-06-14T12:41:47Z
dc.title.none.fl_str_mv Minimising multi-centre radiomics variability through image normalisation: a pilot study
title Minimising multi-centre radiomics variability through image normalisation: a pilot study
spellingShingle Minimising multi-centre radiomics variability through image normalisation: a pilot study
Campello, VM
diagnostic imaging
human
hypertrophic cardiomyopathy
nuclear magnetic resonance imaging
pilot study
procedures
Cardiomyopathy, Hypertrophic
Humans
Magnetic Resonance Imaging
Pilot Projects
title_short Minimising multi-centre radiomics variability through image normalisation: a pilot study
title_full Minimising multi-centre radiomics variability through image normalisation: a pilot study
title_fullStr Minimising multi-centre radiomics variability through image normalisation: a pilot study
title_full_unstemmed Minimising multi-centre radiomics variability through image normalisation: a pilot study
title_sort Minimising multi-centre radiomics variability through image normalisation: a pilot study
dc.creator.none.fl_str_mv Campello, VM
Martin-Isla, C
Izquierdo, C
Guala, A
Palomares, JFR
Vilades, D
Descalzo, ML
Karakas, M
Cavus, E
Raisi-Estabragh, Z
Petersen, SE
Escalera, S
Segui, S
Lekadir, K
author Campello, VM
author_facet Campello, VM
Martin-Isla, C
Izquierdo, C
Guala, A
Palomares, JFR
Vilades, D
Descalzo, ML
Karakas, M
Cavus, E
Raisi-Estabragh, Z
Petersen, SE
Escalera, S
Segui, S
Lekadir, K
author_role author
author2 Martin-Isla, C
Izquierdo, C
Guala, A
Palomares, JFR
Vilades, D
Descalzo, ML
Karakas, M
Cavus, E
Raisi-Estabragh, Z
Petersen, SE
Escalera, S
Segui, S
Lekadir, K
author2_role author
author
author
author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv diagnostic imaging
human
hypertrophic cardiomyopathy
nuclear magnetic resonance imaging
pilot study
procedures
Cardiomyopathy, Hypertrophic
Humans
Magnetic Resonance Imaging
Pilot Projects
topic diagnostic imaging
human
hypertrophic cardiomyopathy
nuclear magnetic resonance imaging
pilot study
procedures
Cardiomyopathy, Hypertrophic
Humans
Magnetic Resonance Imaging
Pilot Projects
description Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features' variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 +/- 0.08 and 0.79 +/- 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 +/- 0.28 and 0.60 +/- 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=12291
https://ddd.uab.cat/record/277673
url https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=12291
https://ddd.uab.cat/record/277673
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv NATURE RESEARCH
publisher.none.fl_str_mv NATURE RESEARCH
dc.source.none.fl_str_mv Scientific Reports
ISSN: 20452322
reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
instname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
instname_str Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
reponame_str r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
collection r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403294997151744
score 15.812429

Similares en LA Referencia