Deep learning based automated delineation of the intraprostatic gross tumour volume in PSMA-PET for patients with primary prostate cancer

•A CNN was trained solely on 18F-PSMA-1007 PET to segment intraprostatic GTVs for Patients with Primary Prostate Cancer.•Tests on internal and external datasets as well as histopathology reference showed a fast GTV segmentation for 18F-PSMA-1007-, 18F-DCFPyL-PSMA- and 68Ga-PSMA-11-PET with high diagnostic accuracy comparable to manual expert contours.•We found that the reconstruction parameters of the PET scanner influence CNN performance.•In our tests the CNN generalized well across multiple tracers even though being only trained on 18F-PSMA-1007. With the increased use of focal radiation dose escalation for primary prostate cancer (PCa), accurate delineation of gross tumor volume (GTV) in prostate-specific membrane antigen PET (PSMA-PET) becomes crucial. Manual approaches are time-consuming and observer dependent. The purpose of this study was to create a deep learning model for the accurate delineation of the intraprostatic GTV in PSMA-PET. A 3D U-Net was trained on 128 different 18F-PSMA-1007 PET images from three different institutions. Testing was done on 52 patients including one independent internal cohort (Freiburg: n = 19) and three independent external cohorts (Dresden: n = 14 18F-PSMA-1007, Boston: Massachusetts General Hospital (MGH): n = 9 18F-DCFPyL-PSMA and Dana-Farber Cancer Institute (DFCI): n = 10 68Ga-PSMA-11). Expert contours were generated in consensus using a validated technique. CNN predictions were compared to expert contours using Dice similarity coefficient (DSC). Co-registered whole-mount histology was used for the internal testing cohort to assess sensitivity/specificity. Median DSCs were Freiburg: 0.82 (IQR: 0.73–0.88), Dresden: 0.71 (IQR: 0.53–0.75), MGH: 0.80 (IQR: 0.64–0.83) and DFCI: 0.80 (IQR: 0.67–0.84), respectively. Median sensitivity for CNN and expert contours were 0.88 (IQR: 0.68–0.97) and 0.85 (IQR: 0.75–0.88) (p = 0.40), respectively. GTV volumes did not differ significantly (p > 0.1 for all comparisons). Median specificity of 0.83 (IQR: 0.57–0.97) and 0.88 (IQR: 0.69–0.98) were observed for CNN and expert contours (p = 0.014), respectively. CNN prediction took 3.81 seconds on average per patient. The CNN was trained and tested on internal and external datasets as well as histopathology reference, achieving a fast GTV segmentation for three PSMA-PET tracers with high diagnostic accuracy comparable to manual experts.