Matthijs C F Cysouw1, Bernard H E Jansen2,3, Tim van de Brug4, Daniela E Oprea-Lager2, Elisabeth Pfaehler5, Bart M de Vries2, Reindert J A van Moorselaar3, Otto S Hoekstra2, André N Vis3, Ronald Boellaard2. 1. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, the Netherlands. m.cysouw@amsterdamumc.nl. 2. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, the Netherlands. 3. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Urology, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, the Netherlands. 4. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Epidemiology and Biostatistics, De Boelelaan, 1117, Amsterdam, the Netherlands. 5. Department of Nuclear Medicine and Molecular Imaging, Medical Imaging Center, University of Groningen, Groningen, the Netherlands.
Abstract
PURPOSE: Quantitative prostate-specific membrane antigen (PSMA) PET analysis may provide for non-invasive and objective risk stratification of primary prostate cancer (PCa) patients. We determined the ability of machine learning-based analysis of quantitative [18F]DCFPyL PET metrics to predict metastatic disease or high-risk pathological tumor features. METHODS: In a prospective cohort study, 76 patients with intermediate- to high-risk PCa scheduled for robot-assisted radical prostatectomy with extended pelvic lymph node dissection underwent pre-operative [18F]DCFPyL PET-CT. Primary tumors were delineated using 50-70% peak isocontour thresholds on images with and without partial-volume correction (PVC). Four hundred and eighty standardized radiomic features were extracted per tumor. Random forest models were trained to predict lymph node involvement (LNI), presence of any metastasis, Gleason score ≥ 8, and presence of extracapsular extension (ECE). For comparison, models were also trained using standard PET features (SUVs, volume, total PSMA uptake). Model performance was validated using 50 times repeated 5-fold cross-validation yielding the mean receiver-operator characteristic curve AUC. RESULTS: The radiomics-based machine learning models predicted LNI (AUC 0.86 ± 0.15, p < 0.01), nodal or distant metastasis (AUC 0.86 ± 0.14, p < 0.01), Gleason score (0.81 ± 0.16, p < 0.01), and ECE (0.76 ± 0.12, p < 0.01). The highest AUCs reached using standard PET metrics were lower than those of radiomics-based models. For LNI and metastasis prediction, PVC and a higher delineation threshold improved model stability. Machine learning pre-processing methods had a minor impact on model performance. CONCLUSION: Machine learning-based analysis of quantitative [18F]DCFPyL PET metrics can predict LNI and high-risk pathological tumor features in primary PCa patients. These findings indicate that PSMA expression detected on PET is related to both primary tumor histopathology and metastatic tendency. Multicenter external validation is needed to determine the benefits of using radiomics versus standard PET metrics in clinical practice.
PURPOSE: Quantitative prostate-specific membrane antigen (PSMA) PET analysis may provide for non-invasive and objective risk stratification of primary prostate cancer (PCa) patients. We determined the ability of machine learning-based analysis of quantitative [18F]DCFPyL PET metrics to predict metastatic disease or high-risk pathological tumor features. METHODS: In a prospective cohort study, 76 patients with intermediate- to high-risk PCa scheduled for robot-assisted radical prostatectomy with extended pelvic lymph node dissection underwent pre-operative [18F]DCFPyL PET-CT. Primary tumors were delineated using 50-70% peak isocontour thresholds on images with and without partial-volume correction (PVC). Four hundred and eighty standardized radiomic features were extracted per tumor. Random forest models were trained to predict lymph node involvement (LNI), presence of any metastasis, Gleason score ≥ 8, and presence of extracapsular extension (ECE). For comparison, models were also trained using standard PET features (SUVs, volume, total PSMA uptake). Model performance was validated using 50 times repeated 5-fold cross-validation yielding the mean receiver-operator characteristic curve AUC. RESULTS: The radiomics-based machine learning models predicted LNI (AUC 0.86 ± 0.15, p < 0.01), nodal or distant metastasis (AUC 0.86 ± 0.14, p < 0.01), Gleason score (0.81 ± 0.16, p < 0.01), and ECE (0.76 ± 0.12, p < 0.01). The highest AUCs reached using standard PET metrics were lower than those of radiomics-based models. For LNI and metastasis prediction, PVC and a higher delineation threshold improved model stability. Machine learning pre-processing methods had a minor impact on model performance. CONCLUSION: Machine learning-based analysis of quantitative [18F]DCFPyL PET metrics can predict LNI and high-risk pathological tumor features in primary PCa patients. These findings indicate that PSMA expression detected on PET is related to both primary tumor histopathology and metastatic tendency. Multicenter external validation is needed to determine the benefits of using radiomics versus standard PET metrics in clinical practice.
Authors: Daniela A Ferraro; Urs J Muehlematter; Helena I Garcia Schüler; Niels J Rupp; Martin Huellner; Michael Messerli; Jan Hendrik Rüschoff; Edwin E G W Ter Voert; Thomas Hermanns; Irene A Burger Journal: Eur J Nucl Med Mol Imaging Date: 2019-09-14 Impact factor: 9.236
Authors: Constantinos Zamboglou; Montserrat Carles; Tobias Fechter; Selina Kiefer; Kathrin Reichel; Thomas F Fassbender; Peter Bronsert; Goeran Koeber; Oliver Schilling; Juri Ruf; Martin Werner; Cordula A Jilg; Dimos Baltas; Michael Mix; Anca L Grosu Journal: Theranostics Date: 2019-04-13 Impact factor: 11.556
Authors: Simon K B Spohn; Alisa S Bettermann; Fabian Bamberg; Matthias Benndorf; Michael Mix; Nils H Nicolay; Tobias Fechter; Tobias Hölscher; Radu Grosu; Arturo Chiti; Anca L Grosu; Constantinos Zamboglou Journal: Theranostics Date: 2021-07-06 Impact factor: 11.556
Authors: Jakoba J Eertink; Elisabeth A G Pfaehler; Sanne E Wiegers; Tim van; Pieternella J Lugtenburg; Otto S Hoekstra; Josée M Zijlstra; Henrica C W de Vet; Ronald Boellaard Journal: J Nucl Med Date: 2021-07-16 Impact factor: 10.057
Authors: Sobhan Moazemi; Annette Erle; Zain Khurshid; Susanne Lütje; Michael Muders; Markus Essler; Thomas Schultz; Ralph A Bundschuh Journal: Ann Transl Med Date: 2021-05