Voxel spacing aware method improves texture features from uneven CT scans
A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture Analysis
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Medical images like CT and MRI scans often have unevenly sized pixels or voxels, which can make analyzing textures tricky. The authors created a software upgrade for PyRadiomics that understands these different voxel sizes without changing the original image data. Their method keeps the texture features accurate by considering the actual physical spacing between pixels, especially when the spacing is uneven. This helps ensure better and more consistent texture analysis across different medical scans.
What this means in practice
- •For medical imaging engineers: Use the spacing-aware PyRadiomics extension to extract consistent texture features from scans with uneven voxel sizes without preprocessing via interpolation.
- •For radiology software developers: Incorporate spacing-aware texture analysis into imaging software to improve quantitative image assessment for clinical decision support systems.
Authors
David Corral Fontecha, Juan Miranda Bautista, Pablo Menendez Fernández-Miranda, Andrea Trapote Fernandez, Lara Lloret Iglesias, Jose A. Vega
Abstract
Radiomic texture features are commonly extracted from anisotropic CT and MRI acquisitions, where identical voxel offsets may represent different physical distances. We implemented and validated a voxel-spacing-aware extension of PyRadiomics that incorporates spacing information without generating interpolated gray levels. The framework operates across the Python frontend, C wrapper, and computational backend. GLCM uses anisotropy-relative feature-level angular aggregation, NGTDM uses anisotropy-relative weighted neighborhood averaging, and GLRLM, GLDM, and GLSZM are computed on a finite-volume zero-order-hold representation derived from the native anisotropic grid. Synthetic 3D phantoms were used for software validation. The modified implementation reproduced standard PyRadiomics exactly when spacing-aware mode was disabled and remained equivalent under isotropic spacing across 75 texture features. Under anisotropic spacing, the method selectively modified texture families and was numerically distinct from nearest-neighbor, linear, and B-spline resampling. Computational profiling showed moderate runtime and memory increases, while sensitivity analyses quantified finite-volume rounding effects and confirmed that spacing-aware differences persisted across binWidth settings. The framework provides a backward-compatible technical basis for future evaluation of spacing-aware radiomics in heterogeneous medical imaging datasets.