The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and 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…

• NS
  National Science Foundation

  Award: 320030_176052
• W
  Wellcome

  Award: WT 203148/Z/16/Z
• CI
  Canadian Institute for Advanced Research
• UR
  UK Research and Innovation
• CR
  Cancer Research UK

  Awards: C1519, A27066, C4278/A27066, C1519/A28682
• KC
  King's College London

  Award: WT 203148/Z/16/Z
• SN
  Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

  Awards: 205320_179069, CRSII5_183478, 203148, 320030_176052, 310030_170159
• NS
  Natural Sciences and Engineering Research Council of Canada

  Awards: RGPIN-2019-06467, RGPIN-2019
• EA
  Engineering and Physical Sciences Research Council

  Awards: WT 203148/Z/16/Z, N509449/1, EP/N509449/1, WT 203148/Z/16/, 203148/Z/16/Z
• CF
  Centre For Medical Engineering, King’s College London

  Awards: 203148/Z/16/Z, WT 203148/Z/16/Z
• NC
  National Cancer Institute

  Awards: P30CA008748, U24CA189523, 30CA008748, U01CA242871