The image biomarker standardization initiative: Standardized convolutional filters for reproducible radiomics and enhanced clinical insights

Whybra, Philip, Zwanenburg, Alex, Andrearczyk, Vincent, Schaer, Roger, Apte, Aditya P., Ayotte, Alexandre, Baheti, Bhakti, Bakas, Spyridon, Bettinelli, Andrea, Boellaard, Ronald, Boldrini, Luca, Buvat, Irène, Cook, Gary J. R., Dietsche, Florian, Dinapoli, Nicola, Gabryś, Hubert S., Goh, Vicky, Guckenberger, Matthias, Hatt, Mathieu, Hosseinzadeh, Mahdi, Iyer, Aditi, Lenkowicz, Jacopo, Loutfi, Mahdi A. L., Löck, Steffen, Marturano, Francesca, Morin, Olivier, Nioche, Christophe, Orlhac, Fanny, Pati, Sarthak, Rahmim, Arman, Rezaeijo, Seyed Masoud, Rookyard, Christopher G., Salmanpour, Mohammad R., Schindele, Andreas, Shiri, Isaac, Spezi, Emiliano ORCID: https://orcid.org/0000-0002-1452-8813, Tanadini-Lang, Stephanie, Tixier, Florent, Upadhaya, Taman, Valentini, Vincenzo, van Griethuysen, Joost J. M., Yousefirizi, Fereshteh, Zaidi, Habib, Müller, Henning, Vallières, Martin and Depeursinge, Adrien 2024. The image biomarker standardization initiative: Standardized convolutional filters for reproducible radiomics and enhanced clinical insights. Radiology 310 (2) 10.1148/radiol.231319

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution No Derivatives. Download (1MB) | Preview

Abstract

Standardizing convolutional filters that enhance specific structures and patterns in medical imaging enables reproducible radiomics analyses, improving consistency and reliability for enhanced clinical insights. 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.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Radiological Society of North America
ISSN:	0033-8419
Date of First Compliant Deposit:	13 February 2024
Date of Acceptance:	5 September 2023
Last Modified:	06 Mar 2024 23:56
URI:	https://orca.cardiff.ac.uk/id/eprint/166232

Actions (repository staff only)

Edit Item