article Open AccessTop 1% cited

Intrinsic dependencies of <scp>CT</scp> radiomic features on voxel size and number of gray levels

Medical Physics · 2017 · Vol. 44(3) · pp. 1050–1062

Muhammad Shafiq‐ul‐Hassan(University of South Florida)Geoffrey Zhang(University of South Florida)Kujtim Latifi(University of South Florida)Ghanim Ullah(University of South Florida)Dylan Hunt(Moffitt Cancer Center)Yoganand Balagurunathan(Moffitt Cancer Center)Mahmoud A. Abdalah(Moffitt Cancer Center)Matthew B. Schabath(Moffitt Cancer Center)Dmitry Goldgof(University of South Florida)Dennis Mackin(The University of Texas MD Anderson Cancer Center)Laurence E. Court(The University of Texas MD Anderson Cancer Center)Robert J. Gillies(Moffitt Cancer Center)Eduardo G. Moros✉(University of South Florida)

View via DOI Publisher page

Abstract

Voxel-size resampling is an appropriate pre-processing step for image datasets acquired with variable voxel sizes to obtain more reproducible CT features. We found that some of the radiomics features were voxel size and gray-level discretization-dependent. The introduction of normalizing factors in their definitions greatly reduced or removed these dependencies.

Radiomics and Machine Learning in Medical Imaging Advanced X-ray and CT Imaging Medical Imaging Techniques and ApplicationsImaging phantomPixelVoxelArtificial intelligenceComputer scienceComputer visionIterative reconstructionMaterials scienceNuclear medicineMedicine