Show simple item record

dc.contributor.authorEscudero Sanchez, Lorena
dc.contributor.authorRundo, Leonardo
dc.contributor.authorGill, Andrew B
dc.contributor.authorHoare, Matthew
dc.contributor.authorMendes Serrao, Eva
dc.contributor.authorSala, Evis
dc.description.abstractRadiomic 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.
dc.description.sponsorshipL.E.S. and E.S. were supported by the CRUK National Cancer Imaging Translational Accelerator (NCITA) [C42780/A27066]. L.R., A.B.G. and E.S. were supported by The Mark Foundation for Cancer Research and Cancer Research UK (CRUK) Cambridge Centre [C9685/A25177]. M.H. was supported by a CRUK-OHSU Early Detection Project Award [C52489/A29681] and a CRUK HCC Accelerator Award [C18873/A26813]. E.M.S. was supported by the Academy of Medical Sciences, the Wellcome Trust, the Medical Research Council (MRC), the British Heart Foundation, Versus Arthritis, Diabetes UK and the British Thoracic Society (Helen and Andrew Douglas bequest) Starter Grant award [SGL019/1007]. Additional support has been provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre [BRC-1215-20014] and from the Wellcome Trust Innovator Award RG98755.
dc.publisherSpringer Science and Business Media LLC
dc.rightsAttribution 4.0 International (CC BY 4.0)
dc.titleRobustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle.
prism.publicationNameSci Rep
dc.contributor.orcidEscudero Sanchez, Lorena [0000-0003-3464-9206]
dc.contributor.orcidRundo, Leonardo [0000-0003-3341-5483]
dc.contributor.orcidGill, Andrew [0000-0002-9287-9563]
dc.contributor.orcidHoare, Matthew [0000-0001-5990-9604]
dc.contributor.orcidSala, Evis [0000-0002-5518-9360]
rioxxterms.typeJournal Article/Review
pubs.funder-project-idCancer Research UK (via Newcastle University) (BH183441)
pubs.funder-project-idCancer Research UK (C52489/A29681)
pubs.funder-project-idCancer Research UK (A19924)
pubs.funder-project-idCancer Research UK (C96/A25177)
pubs.funder-project-idNational Institute for Health Research (IS-BRC-1215-20014)

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY 4.0)