TY - JOUR T1 - Intraprostatic Tumor Segmentation on PSMA PET Images in Patients with Primary Prostate Cancer with a Convolutional Neural Network JF - Journal of Nuclear Medicine JO - J Nucl Med SP - 823 LP - 828 DO - 10.2967/jnumed.120.254623 VL - 62 IS - 6 AU - Dejan Kostyszyn AU - Tobias Fechter AU - Nico Bartl AU - Anca L. Grosu AU - Christian Gratzke AU - August Sigle AU - Michael Mix AU - Juri Ruf AU - Thomas F. Fassbender AU - Selina Kiefer AU - Alisa S. Bettermann AU - Nils H. Nicolay AU - Simon Spohn AU - Maria U. Kramer AU - Peter Bronsert AU - Hongqian Guo AU - Xuefeng Qiu AU - Feng Wang AU - Christoph Henkenberens AU - Rudolf A. Werner AU - Dimos Baltas AU - Philipp T. Meyer AU - Thorsten Derlin AU - Mengxia Chen AU - Constantinos Zamboglou Y1 - 2021/06/01 UR - http://jnm.snmjournals.org/content/62/6/823.abstract N2 - Accurate delineation of the intraprostatic gross tumor volume (GTV) is a prerequisite for treatment approaches in patients with primary prostate cancer (PCa). Prostate-specific membrane antigen PET (PSMA PET) may outperform MRI in GTV detection. However, visual GTV delineation underlies interobserver heterogeneity and is time consuming. The aim of this study was to develop a convolutional neural network (CNN) for automated segmentation of intraprostatic tumor (GTV-CNN) in PSMA PET. Methods: The CNN (3D U-Net) was trained on the 68Ga-PSMA PET images of 152 patients from 2 different institutions, and the training labels were generated manually using a validated technique. The CNN was tested on 2 independent internal (cohort 1: 68Ga-PSMA PET, n = 18 and cohort 2: 18F-PSMA PET, n = 19) and 1 external (cohort 3: 68Ga-PSMA PET, n = 20) test datasets. Accordance between manual contours and GTV-CNN was assessed with the Dice-Sørensen coefficient (DSC). Sensitivity and specificity were calculated for the 2 internal test datasets (cohort 1: n = 18, cohort 2: n = 11) using whole-mount histology. Results: The median DSCs for cohorts 1–3 were 0.84 (range: 0.32–0.95), 0.81 (range: 0.28–0.93), and 0.83 (range: 0.32–0.93), respectively. Sensitivities and specificities for the GTV-CNN were comparable with manual expert contours: 0.98 and 0.76 (cohort 1) and 1 and 0.57 (cohort 2), respectively. Computation time was around 6 s for a standard dataset. Conclusion: The application of a CNN for automated contouring of intraprostatic GTV in 68Ga-PSMA and 18F-PSMA PET images resulted in a high concordance with expert contours and in high sensitivities and specificities in comparison with histology as a reference. This robust, accurate and fast technique may be implemented for treatment concepts in primary prostate cancer. The trained model and the study’s source code are available in an open source repository. ER -