Jake Kendrick1, Roslyn J Francis2,3, Ghulam Mubashar Hassan4, Pejman Rowshanfarzad4, Jeremy S L Ong5, Martin A Ebert4,6,7. 1. School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia. jake.kendrick@research.uwa.edu.au. 2. Medical School, University of Western Australia, Crawley, WA, Australia. 3. Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Perth, WA, Australia. 4. School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia. 5. Department of Nuclear Medicine, Fiona Stanley Hospital, Murdoch, WA, Australia. 6. Department of Radiation Oncology, Sir Charles Gairdner Hospital, Perth, WA, Australia. 7. 5D Clinics, Claremont, WA, Australia.
Abstract
PURPOSE: This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [68Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers. METHODS: Three hundred thirty-seven [68Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLVauto) and total lesional uptake (TLUauto) were calculated from the automated segmentations, and Kaplan-Meier analysis was used to assess biomarker relationship with patient overall survival. RESULTS: At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan-Meier analysis of TLVauto and TLUauto showed they were significantly associated with patient overall survival (both p < 0.005). CONCLUSION: The fully automated assessment of whole-body [68Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival. TRIAL REGISTRATION: This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.
PURPOSE: This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [68Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers. METHODS: Three hundred thirty-seven [68Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLVauto) and total lesional uptake (TLUauto) were calculated from the automated segmentations, and Kaplan-Meier analysis was used to assess biomarker relationship with patient overall survival. RESULTS: At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan-Meier analysis of TLVauto and TLUauto showed they were significantly associated with patient overall survival (both p < 0.005). CONCLUSION: The fully automated assessment of whole-body [68Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival. TRIAL REGISTRATION: This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.
Authors: Ali Afshar-Oromieh; Eleni Avtzi; Frederik L Giesel; Tim Holland-Letz; Heinz G Linhart; Matthias Eder; Michael Eisenhut; Silvan Boxler; Boris A Hadaschik; Clemens Kratochwil; Wilko Weichert; Klaus Kopka; Jürgen Debus; Uwe Haberkorn Journal: Eur J Nucl Med Mol Imaging Date: 2014-11-20 Impact factor: 9.236
Authors: Rafael Tourinho-Barbosa; Victor Srougi; Igor Nunes-Silva; Mohammed Baghdadi; Gregory Rembeyo; Sophie S Eiffel; Eric Barret; Francois Rozet; Marc Galiano; Xavier Cathelineau; Rafael Sanchez-Salas Journal: Int Braz J Urol Date: 2018 Jan-Feb Impact factor: 1.541
Authors: Oliver Sartor; Johann de Bono; Kim N Chi; Karim Fizazi; Ken Herrmann; Kambiz Rahbar; Scott T Tagawa; Luke T Nordquist; Nitin Vaishampayan; Ghassan El-Haddad; Chandler H Park; Tomasz M Beer; Alison Armour; Wendy J Pérez-Contreras; Michelle DeSilvio; Euloge Kpamegan; Germo Gericke; Richard A Messmann; Michael J Morris; Bernd J Krause Journal: N Engl J Med Date: 2021-06-23 Impact factor: 91.245
Authors: Elisabeth Svensson; Christian F Christiansen; Sinna P Ulrichsen; Mikael R Rørth; Henrik T Sørensen Journal: BMJ Open Date: 2017-09-11 Impact factor: 2.692
Authors: Indrani Bhattacharya; Yash S Khandwala; Sulaiman Vesal; Wei Shao; Qianye Yang; Simon J C Soerensen; Richard E Fan; Pejman Ghanouni; Christian A Kunder; James D Brooks; Yipeng Hu; Mirabela Rusu; Geoffrey A Sonn Journal: Ther Adv Urol Date: 2022-10-10