Related Experiment Video
Updated: May 5, 2026

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
Published on: January 8, 2018
The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and
Philip Whybra1, Alex Zwanenburg1, Vincent Andrearczyk1
1From the School of Engineering, Cardiff University, Cardiff, United Kingdom (P.W., E.S.); OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany (A.Z., S.L.); National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and Helmholtz Association/Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Fetscherstrasse 74, PF 41 Dresden 01307, Germany (A.Z.); Institute of Informatics, University of Applied Sciences and Arts Western Switzerland (HES-SO), Sierre, Switzerland (V.A., R.S., H.M., A.D.); Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY (A.P.A., A.I.); Department of Computer Science, Université de Sherbrooke, Sherbrooke, QC, Canada (A.A., M.A.L.L., M.V.); Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, Pa (B.B., S.B., S.P.); Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (B.B., S.B., S.P.); Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (B.B., S.B., S.P.); Division of Computational Pathology, Department of Pathology and Laboratory Medicine, Indiana University School of Medicine, Indianapolis, Ind (B.B., S.B., S.P.); Department of Medical Physics, Veneto Institute of Oncology IOV-IRCCS, Padua, Italy (A.B., F.M.); Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands (R.B.); Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy (L.B., N.D., J.L.); Institut Curie, Université PSL, Inserm U1288, Laboratoire d'Imagerie Translationnelle en Oncologie, Orsay, France (I.B., C.N., F.O.); Department of Cancer Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom (G.J.R.C., V.G., C.G.R.); Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland (F.D., H.S.G., M.G., S.T.); Department of Radiology, Guy's & St Thomas' NHS Foundation Trust, London, United Kingdom (V.G.); LaTIM, INSERM, UMR 1101, Université de Bretagne-Occidentale, Brest, France (M. Hatt, F.T.); Technological Virtual Collaboration (TECVICO Corp), Vancouver, Canada (M. Hosseinzadeh, M.R.S.); Department of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran (M. Hosseinzadeh); Department of Radiation Oncology, University of California San Francisco, San Francisco, Calif (O.M., T.U.); Departments of Radiology and Physics, University of British Columbia, Vancouver, Canada (A.R.); Department of Medical Physics, Faculty of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran (S.M.R.); Repository Unit, Cancer Research UK National Cancer Imaging Translational Accelerator, United Kingdom (C.G.R.); Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada (M.R.S., F.Y.); Department of Nuclear Medicine, Universitätsklinikum Augsburg, Augsburg, Germany (A.S.); Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland (I.S., H.Z.); Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Switzerland (I.S.); Department of Diagnostic Imaging, Oncological Radiotherapy, and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy (V.V.); Department of Radiological and Hematological Sciences, Università Cattolica del Sacro Cuore-Milano, Milan, Italy (V.V.); Department of Radiology, The Netherlands Cancer Institute, Amsterdam, the Netherlands (J.J.M.v.G.); Department of Radiology, UMC Utrecht, Utrecht, the Netherlands (J.J.M.v.G.); Centre de Recherche du Centre Hospitalier Universitaire de Sherbrooke (CHUS), Sherbrooke, Canada (M.V.); and Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital (CHUV), Lausanne, Switzerland (A.D.).
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.
More Related Videos
Related Concept Videos
Imaging Studies for Cardiovascular System IV: CMRI
Imaging Studies III: Computed Tomography

