Automated F18-FDG PET/CT image quality assessment using deep neural networks on a latest 6-ring digital detector system

To evaluate whether a machine learning classifier can evaluate image quality of maximum intensity projection (MIP) images from F18-FDG-PET scans. A total of 400 MIP images from F18-FDG-PET with simulated decreasing acquisition time (120 s, 90 s, 60 s, 30 s and 15 s per bed-position) using block sequential regularized expectation maximization (BSREM) with a beta-value of 450 and 600 were created. A machine learning classifier was fed with 283 images rated “sufficient image quality” and 117 images rated “insufficient image quality”. The classification performance of the machine learning classifier was assessed by calculating sensitivity, specificity, and area under the receiver operating characteristics curve (AUC) using reader-based classification as the target. Classification performance of the machine learning classifier was AUC 0.978 for BSREM beta 450 and 0.967 for BSREM beta 600. The algorithm showed a sensitivity of 89% and 94% and a specificity of 94% and 94% for the reconstruction BSREM 450 and 600, respectively. Automated assessment of image quality from F18-FDG-PET images using a machine learning classifier provides equivalent performance to manual assessment by experienced radiologists.