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

Fournier, L, Costaridou, L, Bidaut, Luc , Michoux, N, Lecouvet, F, de Geus-Oei, L-F, Boellaard, R, Oprea-Lager, D E, Obuchowski, N, Caroli, A, Kunz, W G, Oei, E H, O'Connor, J P B, Mayerhoefer, M E, Franca, M, Alberich-Bayarri, A, Deroose, C M, Loewe, C, Manniesing, R, Caramella, C, Lopci, E, Lassau, N, Persson, A, Achten, R, Rosendahl, K, Clement, O, Kotter, E, Golay, X, Smits, M, Dewey, M, Sullivan, D, van der Lugt, A and deSouza, N M Incorporating radiomics into clinical trials: expert consensus on considerations for data-driven compared to biologically-driven quantitative biomarkers.

Documents
Incorporating radiomics into clinical trials: expert consensus on considerations for data-driven compared to biologically-driven quantitative biomarkers
Accepted Manuscript
[img] PDF
EURA-D-20-03018_R1_26oct20revised.pdf - Whole Document
Restricted to Repository staff only

1MB
Item Type:Article
Item Status:Live Archive

Abstract

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.

Keywords:Radiology, Statistics & Numerical data, Standardization, Validation studies, Clinical Trial
Subjects:B Subjects allied to Medicine > B820 Radiology
G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G150 Mathematical Modelling
F Physical Sciences > F350 Medical Physics
G Mathematical and Computer Sciences > G300 Statistics
G Mathematical and Computer Sciences > G760 Machine Learning
A Medicine and Dentistry > A900 Others in Medicine and Dentistry
B Subjects allied to Medicine > B800 Medical Technology
ID Code:43205
Deposited On:04 Dec 2020 12:58

Repository Staff Only: item control page