Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Abstract Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously publ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	James C. Korte, Carlos Cardenas, Nicholas Hardcastle, Tomas Kron, Jihong Wang, Houda Bahig, Baher Elgohari, Rachel Ger, Laurence Court, Clifton D. Fuller, Sweet Ping Ng
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/54d1a476d90147e2bd7eb9f82e0cca6a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:54d1a476d90147e2bd7eb9f82e0cca6a
record_format	dspace
spelling	oai:doaj.org-article:54d1a476d90147e2bd7eb9f82e0cca6a2021-12-02T17:51:31ZRadiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer10.1038/s41598-021-96600-42045-2322https://doaj.org/article/54d1a476d90147e2bd7eb9f82e0cca6a2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96600-4https://doaj.org/toc/2045-2322Abstract Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.James C. KorteCarlos CardenasNicholas HardcastleTomas KronJihong WangHouda BahigBaher ElgohariRachel GerLaurence CourtClifton D. FullerSweet Ping NgNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q James C. Korte Carlos Cardenas Nicholas Hardcastle Tomas Kron Jihong Wang Houda Bahig Baher Elgohari Rachel Ger Laurence Court Clifton D. Fuller Sweet Ping Ng Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
description	Abstract Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.
format	article
author	James C. Korte Carlos Cardenas Nicholas Hardcastle Tomas Kron Jihong Wang Houda Bahig Baher Elgohari Rachel Ger Laurence Court Clifton D. Fuller Sweet Ping Ng
author_facet	James C. Korte Carlos Cardenas Nicholas Hardcastle Tomas Kron Jihong Wang Houda Bahig Baher Elgohari Rachel Ger Laurence Court Clifton D. Fuller Sweet Ping Ng
author_sort	James C. Korte
title	Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
title_short	Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
title_full	Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
title_fullStr	Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
title_full_unstemmed	Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
title_sort	radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/54d1a476d90147e2bd7eb9f82e0cca6a
work_keys_str_mv	AT jamesckorte radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT carloscardenas radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT nicholashardcastle radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT tomaskron radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT jihongwang radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT houdabahig radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT baherelgohari radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT rachelger radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT laurencecourt radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT cliftondfuller radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer AT sweetpingng radiomicsfeaturestabilityofopensourcesoftwareevaluatedonapparentdiffusioncoefficientmapsinheadandneckcancer
_version_	1718379225495371776

Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Ejemplares similares