Identification of low variability textural features for heterogeneity quantification of 18F-FDG PET/CT imaging

Objective: To identify those textural features that are insensitive to both technical and biological factors in order to standardise heterogeneity studies on F-18-FDG PET imaging. Materials and methods: Two different studies were performed. First, nineteen series from a cylindrical phantom filled with different F-18-FDG activity concentration were acquired and reconstructed using three different protocols. Seventy-two texture features were calculated inside a circular region of interest. The variability of each feature was obtained. Second, the data for 15 patients showing non-pathological liver were acquired. Anatomical and physiological features such as patient's weight, height, body mass index, metabolic active volume, blood glucose level, SUV and SUV standard deviation were also recorded. A liver covering region of interest was delineated and low variability textural features calculated in each patient. Finally, a multivariate Spearman's correlation analysis between biological factors and texture features was performed. Results: Only eight texture features analysed show small variability (<5%) with activity concentration and reconstruction protocol making them suitable for heterogeneity quantification. On the other hand, there is a high statistically significant correlation between MAV and entropy (P< 0.05). Entropy feature is, indeed, correlated (P< 0.05) with all patient parameters, except body mass index. Conclusions: The textural features that are correlated with neither technical nor biological factors are run percentage, short-zone emphasis and intensity, making them suitable for quantifying functional changes or classifying patients. Other textural features are correlated with technical and biological factors and are, therefore, a source of errors if used for this purpose. (C) 2016 Elsevier Espana, S.L.U. y SEMNIM. All rights reserved.