Bridging the gap between micro- and macro-scales in medical imaging with textural analysis – A biological basis for CT radiomics classifiers?

• Published in: Physica medica Vol. 72; pp. 142 - 151
• Main Authors: Geady, C., Keller, H., Siddiqui, I., Bilkey, J., Dhani, N.C., Jaffray, D.A.
• Format: Journal Article
• Language: English
• Published: Italy Elsevier Ltd 01-04-2020
• Subjects: Feature stability; Grey-level co-occurrence; Hypoxia; Image processing; Image Processing, Computer-Assisted - methods; Pancreatic cancer; Pathology; Personalized medicine; Quantitative imaging; Radiomics; Texture; Tomography, X-Ray Computed; Grey-level co-occurrence; Pathology; Image processing; Pancreatic cancer; Hypoxia; Quantitative imaging; Personalized medicine; Texture; Radiomics; Feature stability
• ISSN: 1120-1797; 1724-191X
• DOI: 10.1016/j.ejmp.2020.03.018

•A transfer function was developed to convert classified pathology images to linear attenuation maps.•Grey-Level Co-occurrence Matrix (GLCM) texture features were calculated from the attenuation maps and compared to pathology features.•A simplified model of spatial frequency loss in computed tomography (CT) was applied to the attenuation maps.•GLCM texture features were assessed a function of spatial frequency loss.
Studies suggest there is utility in computed tomography (CT) radiomics for pancreatic disease; however, the precise biological interpretation of its features is unclear. In this manuscript, we present a novel approach towards this interpretation by investigating sub-micron tissue structure using digital pathology.
A classification-to attenuation (CAT) function was developed and applied to digital pathology images to create sub-micron linear attenuation maps. From these maps, grey level co-occurrence matrix (GLCM) features were extracted and compared to pathology features. To simulate the spatial frequency loss in a CT scanner, the attenuation maps were convolved with a point spread function (PSF) and subsequently down-sampled. GLCM features were extracted from these down-sampled maps to assess feature stability as a function of spatial frequency loss.
Two GLCM features were shown to be strongly and positively correlated (r = 0.8) with underlying characteristics of the tumor microenvironment, namely percent pimonidazole staining in the tumor. All features underwent marked change as a function of spatial frequency loss; progressively larger spatial frequency losses resulted in progressively larger inter-tumor standard deviations; two GLCM features exhibited stability up to a 100 µm pixel size.
This work represents a necessary step towards understanding the biological significance of radiomics. Our preliminary results suggest that cellular metrics of pimonidazole-detectable hypoxia correlate with sub-micron attenuation coefficient texture; however, the consistency of these textures in face of spatial frequency loss is detrimental for robust radiomics. Further study in larger data sets may elucidate additional, potentially more robust features of biologic and clinical relevance.