Journal Articles Radiology Year : 2024

The Image Biomarker Standardization Initiative: Standardized convolutional filters for quantitative radiomics

1 Cardiff University
2 HES-SO - Haute École spécialisée de Suisse occidentale = HES-SO University of Applied Sciences and Arts Western Switzerland = Fachhochschule Westschweiz [Schweiz]
3 MSKCC - Memorial Sloan Kettering Cancer Center
4 UdeS - Université de Sherbrooke = University of Sherbrooke [Sherbrooke]
5 University of Pennsylvania [Philadelphia]
6 IOV-IRCCS - Istituto Oncologico Veneto = Veneto Institute of Oncology [Padua]
7 Amsterdam UMC - Amsterdam University Medical Centers
8 Fondazione Policlinico Universitario Agostino Gemelli IRCCS
9 LITO - Laboratoire d'Imagerie Translationnelle en Oncologie
10 King‘s College London
11 Division of Gastroenterology, University Hospital Zurich, Zurich, Switzerland.
12 University hospital of Zurich [Zurich]
13 UZH - Universität Zürich [Zürich] = University of Zurich
14 LaTIM - Laboratoire de Traitement de l'Information Medicale
15 TECVICO Corp - Technological Virtual Collaboration , Vancouver, Canada
16 TU Dresden - Technische Universität Dresden = Dresden University of Technology
17 UC San Francisco - University of California [San Francisco]
18 Indiana University School of Medicine
19 UBC - University of British Columbia [Canada]
20 AJUMS - Ahvaz Jundishapur University of Medical Sciences
21 UNIA - Universität Augsburg [Deutschland] = University of Augsburg [Germany] = Université d'Augsbourg [Allemagne]
22 HUG - Hôpitaux Universitaires de Genève = University Hospital of Geneva [Genève]
23 USZ - Universitätsspital Zürich
24 Cedars-Sinai Medical Center
25 NKI - Netherlands Cancer Institute
26 Utrecht Brain Center [Utrecht]
27 BCCRC - BC Cancer Agency Research Centre
28 Geneva University Hospitals and Geneva University
29 CSSS-IUGS - Institut Universitaire de Gériatrie de Sherbrooke
30 CHUV - Centre Hospitalier Universitaire Vaudois = Lausanne University Hospital [Lausanne]
Gary Cook
Hubert Gabryś
Vicky Goh
Christopher Rookyard
Emiliano Spezi
Taman Upadhaya

Abstract

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Fichier principal
Vignette du fichier
Whybra2023_HAL.pdf (2.09 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

inserm-04783231 , version 1 (14-11-2024)

Licence

Identifiers

Cite

Philip Whybra, Alex Zwanenburg, Vincent Andrearczyk, Roger Schaer, Aditya Apte, et al.. The Image Biomarker Standardization Initiative: Standardized convolutional filters for quantitative radiomics. Radiology, 2024, 310 (2), pp.e231319. ⟨10.1148/radiol.231319⟩. ⟨inserm-04783231⟩
183 View
453 Download

Altmetric

Share

  • More