SU‐E‐J‐251: Incorporation of Pre‐Therapy 18F‐FDG Uptake with CT Texture Features in a Predictive Model for Radiation Pneumonitis Development

Abstract

Purpose:To determine whether the addition of standardized uptake value (SUV) statistical variables to CT lung texture features can improve a predictive model of radiation pneumonitis (RP) development in patients undergoing radiation therapy.Methods:Anonymized data from 96 esophageal cancer patients (18 RP‐positive cases of Grade ≥ 2) were retrospectively collected including pre‐therapy PET/CT scans, pre‐/posttherapy diagnostic CT scans and RP status. Twenty texture features (firstorder, fractal, Laws’ filter and gray‐level co‐occurrence matrix) were calculated from diagnostic CT scans and compared in anatomically matched regions of the lung. The mean, maximum, standard deviation, and 50th–95th percentiles of the SUV values for all lung voxels in the corresponding PET scans were acquired. For each texture feature, a logistic regression‐based classifier consisting of (1) the average change in that texture feature value between the pre‐ and post‐therapy CT scans and (2) the pre‐therapy SUV standard deviation (SUVSD) was created. The RP‐classification performance of each logistic regression model was compared to the performance of its texture feature alone by computing areas under the receiver operating characteristic curves (AUCs). T‐tests were performed to determine whether the mean AUC across texture features changed significantly when SUVSD was added to the classifier.Results:The AUC for single‐texturefeature classifiers ranged from 0.58–0.81 in high‐dose (≥ 30 Gy) regions of the lungs and from 0.53–0.71 in low‐dose (< 10 Gy) regions. Adding SUVSD in a logistic regression model using a 50/50 data partition for training and testing significantly increased the mean AUC by 0.08, 0.06 and 0.04 in the low‐, medium‐ and high‐dose regions, respectively.Conclusion:Addition of SUVSD from a pre‐therapy PET scan to a single CT‐based texture feature improves RP‐classification performance on average. These findings demonstrate the potential for more accurate prediction of RP using information from multiple imaging modalities.Supported, in part, by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under grant number T32 EB002103; SGA receives royalties and licensing fees through the University of Chicago for computer‐aided diagnosis technology. HA receives royalties through the University of Chicago for computer‐aided diagnosis technology.