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

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Julius C. Holzschuh - , University Medical Center Freiburg (Author)
  • Michael Mix - , University Medical Center Freiburg (Author)
  • Juri Ruf - , University Medical Center Freiburg (Author)
  • Tobias Hölscher - , Department of Radiation Oncology, University Hospital Carl Gustav Carus Dresden (Author)
  • Jörg Kotzerke - , Department of Nuclear Medicine, University Hospital Carl Gustav Carus Dresden (Author)
  • Alexis Vrachimis - , German Oncology Center - University Hospital of the European University (Author)
  • Paul Doolan - , German Oncology Center - University Hospital of the European University (Author)
  • Harun Ilhan - , Hospital of the Ludwig-Maximilians-University (LMU) Munich (Author)
  • Ioana M. Marinescu - , University Medical Center Freiburg (Author)
  • Simon K. B. Spohn - , University Medical Center Freiburg (Author)
  • Tobias Fechter - , University Medical Center Freiburg (Author)
  • Dejan Kuhn - , University Medical Center Freiburg (Author)
  • Peter Bronsert - , University Medical Center Freiburg (Author)
  • Christian Gratzke - , University Medical Center Freiburg (Author)
  • Radu Grosu - , Vienna University of Technology (Author)
  • Sophia C. Kamran - , Massachusetts General Hospital (Author)
  • Pedram Heidari - , Massachusetts General Hospital (Author)
  • Thomas S. C. Ng - , Harvard University (Author)
  • Arda Könik - , Harvard University (Author)
  • Anca-Ligia Grosu - , University Medical Center Freiburg (Author)
  • Constantinos Zamboglou - , European University Cyprus (Author)

Abstract

PURPOSE: 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.

METHODS: 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.

RESULTS: 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.

CONCLUSION: 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.

Details

Original languageEnglish
Article number109774
JournalRadiotherapy and Oncology
Volume188
Publication statusPublished - Nov 2023
Peer-reviewedYes

External IDs

Scopus 85172335022

Keywords

Sustainable Development Goals

Keywords

  • Male, Humans, Tumor Burden, Positron Emission Tomography Computed Tomography/methods, Deep Learning, Radiotherapy Planning, Computer-Assisted/methods, Prostatic Neoplasms/diagnostic imaging

Library keywords