Artificial intelligence-based versus manual assessment of prostate cancer in the prostate gland: a method comparison study

Aim: To test the feasibility of a fully automated artificial intelligence-based method providing PET measures of prostate cancer (PCa). Methods: A convolutional neural network (CNN) was trained for automated measurements in ¹⁸F-choline (FCH) PET/CT scans obtained prior to radical prostatectomy (RP) in 45 patients with newly diagnosed PCa. Automated values were obtained for prostate volume, maximal standardized uptake value (SUV _max), mean standardized uptake value of voxels considered abnormal (SUV _mean) and volume of abnormal voxels (Vol _abn). The product SUV _mean × Vol _abn was calculated to reflect total lesion uptake (TLU). Corresponding manual measurements were performed. CNN-estimated data were compared with the weighted surgically removed tissue specimens and manually derived data and related to clinical parameters assuming that 1 g ≈ 1 ml of tissue. Results: The mean (range) weight of the prostate specimens was 44 g (20–109), while CNN-estimated volume was 62 ml (31–108) with a mean difference of 13·5 g or ml (95% CI: 9·78–17·32). The two measures were significantly correlated (r = 0·77, P<0·001). Mean differences (95% CI) between CNN-based and manually derived PET measures of SUVmax, SUVmean, Vol _abn (ml) and TLU were 0·37 (−0·01 to 0·75), −0·08 (−0·30 to 0·14), 1·40 (−2·26 to 5·06) and 9·61 (−3·95 to 23·17), respectively. PET findings Vol _abn and TLU correlated with PSA (P<0·05), but not with Gleason score or stage. Conclusion: Automated CNN segmentation provided in seconds volume and simple PET measures similar to manually derived ones. Further studies on automated CNN segmentation with newer tracers such as radiolabelled prostate-specific membrane antigen are warranted.