%0 Journal Article
%A Holzschuh, Julius C
%A Mix, Michael
%A Ruf, Juri
%A Hölscher, Tobias
%A Kotzerke, Jörg
%A Vrachimis, Alexis
%A Doolan, Paul
%A Ilhan, Harun
%A Marinescu, Ioana M
%A Spohn, Simon K B
%A Fechter, Tobias
%A Kuhn, Dejan
%A Bronsert, Peter
%A Gratzke, Christian
%A Grosu, Radu
%A Kamran, Sophia C
%A Heidari, Pedram
%A Ng, Thomas S C
%A Könik, Arda
%A Grosu, Anca-Ligia
%A Zamboglou, Constantinos
%T Deep Learning based Automated Delineation of the Intraprostatic Gross Tumour Volume in PSMA-PET for Patients with Primary Prostate Cancer.
%J Radiotherapy and oncology
%V 188
%@ 0167-8140
%C Amsterdam [u.a.]
%I Elsevier Science
%M DKFZ-2023-01336
%P 109774
%D 2023
%Z 2023 Nov:188:109774
%X 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.
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:37394103
%R 10.1016/j.radonc.2023.109774
%U https://inrepo02.dkfz.de/record/277318