Show simple item record

dc.contributor.authorFournier, L
dc.contributor.authorCostaridou, L
dc.contributor.authorBidaut, L
dc.contributor.authorMichoux, N
dc.contributor.authorLecouvet, FE
dc.contributor.authorde Geus-Oei, L-F
dc.contributor.authorBoellaard, R
dc.contributor.authorOprea-Lager, DE
dc.contributor.authorObuchowski, NA
dc.contributor.authorCaroli, A
dc.contributor.authorKunz, WG
dc.contributor.authorOei, EH
dc.contributor.authorO'Connor, JPB
dc.contributor.authorMayerhoefer, ME
dc.contributor.authorFranca, M
dc.contributor.authorAlberich-Bayarri, A
dc.contributor.authorDeroose, CM
dc.contributor.authorLoewe, C
dc.contributor.authorManniesing, R
dc.contributor.authorCaramella, C
dc.contributor.authorLopci, E
dc.contributor.authorLassau, N
dc.contributor.authorPersson, A
dc.contributor.authorAchten, R
dc.contributor.authorRosendahl, K
dc.contributor.authorClement, O
dc.contributor.authorKotter, E
dc.contributor.authorGolay, X
dc.contributor.authorSmits, M
dc.contributor.authorDewey, M
dc.contributor.authorSullivan, DC
dc.contributor.authorvan der Lugt, A
dc.contributor.authordeSouza, NM
dc.contributor.authorEuropean Society Of Radiology
dc.date.accessioned2021-04-08T13:53:12Z
dc.date.available2021-04-08T13:53:12Z
dc.date.issued2021-01-25
dc.identifier.citationEuropean radiology, 2021
dc.identifier.issn0938-7994
dc.identifier.urihttps://repository.icr.ac.uk/handle/internal/4506
dc.identifier.eissn1432-1084
dc.identifier.doi10.1007/s00330-020-07598-8
dc.description.abstractExisting quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. KEY POINTS: • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.
dc.formatPrint-Electronic
dc.languageeng
dc.language.isoeng
dc.rights.urihttps://creativecommons.org/licenses/by/4.0
dc.titleIncorporating radiomics into clinical trials: expert consensus endorsed by the European Society of Radiology on considerations for data-driven compared to biologically driven quantitative biomarkers.
dc.typeJournal Article
dcterms.dateAccepted2020-12-03
rioxxterms.versionVoR
rioxxterms.versionofrecord10.1007/s00330-020-07598-8
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0
rioxxterms.licenseref.startdate2021-01-25
rioxxterms.typeJournal Article/Review
dc.relation.isPartOfEuropean radiology
pubs.notesNot known
pubs.organisational-group/ICR
pubs.organisational-group/ICR/Primary Group
pubs.organisational-group/ICR/Primary Group/ICR Divisions
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Magnetic Resonance
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Quantitative Biomedical Imaging
pubs.organisational-group/ICR
pubs.organisational-group/ICR/Primary Group
pubs.organisational-group/ICR/Primary Group/ICR Divisions
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Magnetic Resonance
pubs.organisational-group/ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Quantitative Biomedical Imaging
pubs.publication-statusPublished
pubs.embargo.termsNot known
icr.researchteamMagnetic Resonance
icr.researchteamQuantitative Biomedical Imaging
icr.researchteamMagnetic Resonanceen_US
icr.researchteamQuantitative Biomedical Imagingen_US
dc.contributor.icrauthordeSouza, Nanditaen
dc.contributor.icrauthorO'Connor, James Patricken


Files in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record

https://creativecommons.org/licenses/by/4.0
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0