Incorporating radiomics into clinical trials: expert consensus on considerations for data-driven compared to biologically driven quantitative biomarkers.

Fournier, Laure

Costaridou, Lena

Bidaut, Luc

Michoux, Nicolas

Lecouvet, Frederic E

de Geus-Oei, Lioe-Fee

Boellaard, Ronald

Oprea-Lager, Daniela E

Obuchowski, Nancy A

Caroli, Anna

Kunz, Wolfgang G

Oei, Edwin H

O'Connor, James PB

Mayerhoefer, Marius E

Franca, Manuela

Alberich-Bayarri, Angel

Deroose, Christophe M

Loewe, Christian

Manniesing, Rashindra

Caramella, Caroline

Lopci, Egesta

Lassau, Nathalie

Persson, Anders

Achten, Rik

Rosendahl, Karen

Clement, Olivier

Kotter, Elmar

Golay, Xavier

Smits, Marion

Dewey, Marc

Sullivan, Daniel C

van der Lugt, Aad

deSouza, Nandita M

European Society Of Radiology

2021-02-01T23:32:27Z

2021-02-01T23:32:27Z

2021-01-25

2021-02-01T23:32:26Z

Existing 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.

10.1007/s00330-020-07598-8

0938-7994

1432-1084

https://hdl.handle.net/10161/22315

eng

Springer Science and Business Media LLC

European radiology

10.1007/s00330-020-07598-8

Clinical trial

Radiology

Standardization

Statistics and numerical data

Validation studies

Incorporating radiomics into clinical trials: expert consensus on considerations for data-driven compared to biologically driven quantitative biomarkers.

Journal article

Sullivan, Daniel C|0000-0002-7556-5650

School of Medicine

Duke Clinical Research Institute

Radiology

Duke

Institutes and Centers

Clinical Science Departments

Published