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

Abstract

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 ¹⁸ F-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.

Keywords: agreement; choline; convolutional neural network; diagnostic imaging; positron emission tomography; prostatic neoplasms.