Background: 18F-FDG PET based radiomics is promising for precision oncology imaging. This work aimsto explore quantitative accuracies of radiomic features (RFs) for low-dose 18F-FDG PET imaging.
Methods: Twenty lung cancer patients were prospectively enrolled and underwent 18F-FDG PET/CTscans. Low-dose PET situations (true counts: 20×106, 15×106, 10×106, 7.5×106, 5×106, 2×106, 1×106, 0.5×106,0.25×106) were simulated by randomly discarding counts from the acquired list-mode data. Each PET imagewas created using the scanner default reconstruction parameters. Each lesion volume of interest (VOI)was obtained via an adaptive contouring method with a threshold of 50% peak standardized uptake value(SUVpeak) in the PET images with full count data and VOIs were copied to the PET images at the reducedcount level. Conventional SUV measures, features calculated from ﬁrst-order statistics (FOS) and texturefeatures (TFs) were calculated. Texture based RF include features calculated from gray-level co-occurrencematrix (GLCM), gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), neighboringgray-level dependence matrix (NGLDM) and neighbor gray-tone difference matrix (NGTDM). Biaspercentage (BP) at different count levels for each RF was calculated.
Results: Fifty-seven lesions with a volume greater than 1.5 cm3 were found (mean volume, 25.7 cm3,volume range, 1.5–245.4 cm3). In comparison with normal total counts, mean SUV (SUVmean) in thelesions, normal lungs and livers, Entropy and sum entropy from GLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the most robust features, with a BP of 5% at the count levelof 1×106 (equivalent to an effective dose of 0.04 mSv) RF including cluster shade from GLCM, long-runlow grey-level emphasis, high grey-level run emphasis and short-run low grey-level emphasis from GLRMexhibited the worst performance with 50% of bias with 20×106 counts (equivalent to an effective dose of0.8 mSv).
Conclusions: In terms of the lesions included in this study, SUVmean, entropy and sum entropy fromGLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the least sensitivefeatures to lowering count.
FDG PET; radiomics; low-dose; quantitative; lung