Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle

Abstract Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lorena Escudero Sanchez, Leonardo Rundo, Andrew B. Gill, Matthew Hoare, Eva Mendes Serrao, Evis Sala
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b37af1e9968a49eb8272a6243d4ac728
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b37af1e9968a49eb8272a6243d4ac728
record_format	dspace
spelling	oai:doaj.org-article:b37af1e9968a49eb8272a6243d4ac7282021-12-02T14:26:20ZRobustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle10.1038/s41598-021-87598-w2045-2322https://doaj.org/article/b37af1e9968a49eb8272a6243d4ac7282021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87598-whttps://doaj.org/toc/2045-2322Abstract Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for liver tumour and muscle, comparing the values of the features in images reconstructed with two different slice thicknesses of 2.0 mm and 5.0 mm. Novel approaches are presented to address the intrinsic dependencies of texture radiomic features, choosing the optimal number of grey levels and correcting for the dependency on volume. With the optimal values and corrections, feature values are compared across thicknesses to identify reproducible features. Normalisation using muscle regions is also described as an alternative approach. With either method, a large fraction of features (75–90%) was found to be highly robust (< 25% difference). The analyses were performed on a homogeneous CT dataset of 43 patients with hepatocellular carcinoma, and consistent results were obtained for both tumour and muscle tissue. Finally, recommended guidelines are included for radiomic studies using variable slice thickness.Lorena Escudero SanchezLeonardo RundoAndrew B. GillMatthew HoareEva Mendes SerraoEvis SalaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Lorena Escudero Sanchez Leonardo Rundo Andrew B. Gill Matthew Hoare Eva Mendes Serrao Evis Sala Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
description	Abstract Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for liver tumour and muscle, comparing the values of the features in images reconstructed with two different slice thicknesses of 2.0 mm and 5.0 mm. Novel approaches are presented to address the intrinsic dependencies of texture radiomic features, choosing the optimal number of grey levels and correcting for the dependency on volume. With the optimal values and corrections, feature values are compared across thicknesses to identify reproducible features. Normalisation using muscle regions is also described as an alternative approach. With either method, a large fraction of features (75–90%) was found to be highly robust (< 25% difference). The analyses were performed on a homogeneous CT dataset of 43 patients with hepatocellular carcinoma, and consistent results were obtained for both tumour and muscle tissue. Finally, recommended guidelines are included for radiomic studies using variable slice thickness.
format	article
author	Lorena Escudero Sanchez Leonardo Rundo Andrew B. Gill Matthew Hoare Eva Mendes Serrao Evis Sala
author_facet	Lorena Escudero Sanchez Leonardo Rundo Andrew B. Gill Matthew Hoare Eva Mendes Serrao Evis Sala
author_sort	Lorena Escudero Sanchez
title	Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
title_short	Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
title_full	Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
title_fullStr	Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
title_full_unstemmed	Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
title_sort	robustness of radiomic features in ct images with different slice thickness, comparing liver tumour and muscle
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b37af1e9968a49eb8272a6243d4ac728
work_keys_str_mv	AT lorenaescuderosanchez robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle AT leonardorundo robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle AT andrewbgill robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle AT matthewhoare robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle AT evamendesserrao robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle AT evissala robustnessofradiomicfeaturesinctimageswithdifferentslicethicknesscomparinglivertumourandmuscle
_version_	1718391390572904448

Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle

Ejemplares similares