The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights

Philip Whybra, Alex Zwanenburg*, Vincent Andrearczyk, Roger Schaer, Aditya P. Apte, Alexandre Ayotte, Bhakti Baheti, Spyridon Bakas, Andrea Bettinelli, Ronald Boellaard, Luca Boldrini, Irène Buvat, Gary J.R. Cook, Florian Dietsche, Nicola Dinapoli, Hubert S. Gabryś, Vicky Goh, Matthias Guckenberger, Mathieu Hatt, Mahdi HosseinzadehAditi Iyer, Jacopo Lenkowicz, Mahdi A.L. Loutfi, Steffen Löck, Francesca Marturano, Olivier Morin, Christophe Nioche, Fanny Orlhac, Sarthak Pati, Arman Rahmim, Seyed Masoud Rezaeijo, Christopher G. Rookyard, Mohammad R. Salmanpour, Andreas Schindele, Isaac Shiri, Emiliano Spezi, Stephanie Tanadini-Lang, Florent Tixier, Taman Upadhaya, Vincenzo Valentini, Joost J.M. van Griethuysen, Fereshteh Yousefirizi, Habib Zaidi, Henning Müller, Martin Vallières, Adrien Depeursinge

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

9 Citations (Scopus)

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.

Original languageEnglish
Article number231319
JournalRadiology
Volume310
Issue number2
DOIs
Publication statusPublished - Feb 2024

Fingerprint

Dive into the research topics of 'The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights'. Together they form a unique fingerprint.

Cite this