No abstract

Purpose To evaluate the performance of combined PET and multiparametric MRI (mpMRI) radiomics for the group-wise prediction of postsurgical Gleason scores (psGSs) in primary prostate cancer (PCa) patients. Methods Patients with PCa, who underwent [68 Ga]Ga-PSMA-11 PET/MRI followed by radical prostatectomy, were included in this retrospective analysis (n = 101). Patients were grouped by psGS in three categories: ISUP grades 1–3, ISUP grade 4, and ISUP grade 5. mpMRI images included T1-weighted, T2-weighted, and apparent diffusion coefficient (ADC) map. Whole-prostate segmentations were performed on each modality, and image biomarker standardization initiative (IBSI)-compliant radiomic features were extracted. Nine support vector machine (SVM) models were trained: four single-modality radiomic models (PET, T1w, T2w, ADC); three PET + MRI double-modality models (PET + T1w, PET + T2w, PET + ADC), and two baseline models (one with patient data, one image-based) for comparison. A sixfold stratified cross-validation was performed, and balanced accuracies (bAcc) of the predictions of the best-performing models were reported and compared through Student’s t-tests. The predictions of the best-performing model were compared against biopsy GS (bGS). Results All radiomic models outperformed the baseline models. The best-performing (mean ± stdv [%]) single-modality model was the ADC model (76 ± 6%), although not significantly better (p > 0.05) than other single-modality models (T1w: 72 ± 3%, T2w: 73 ± 2%; PET: 75 ± 5%). The overall best-performing model combined PET + ADC radiomics (82 ± 5%). It significantly outperformed most other double-modality (PET + T1w: 74 ± 5%, p = 0.026; PET + T2w: 71 ± 4%, p = 0.003) and single-modality models (PET: p = 0.042; T1w: p = 0.002; T2w: p = 0.003), except the ADC-only model (p = 0.138). In this initial cohort, the PET + ADC model outperformed bGS overall (82.5% vs 72.4%) in the prediction of psGS. Conclusion All single- and double-modality models outperformed the baseline models, showing their potential in the prediction of GS, even with an unbalanced cohort. The best-performing model included PET + ADC radiomics, suggesting a complementary value of PSMA-PET and ADC radiomics.

Purpose In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers. Methods In 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework. Results In the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1–87.8] for identification of suspicious uptake sites, 77% (CI: 70.0–83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage. Conclusion The evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.

No abstract

Background In patients with increasing PSA and suspicion for prostate cancer, but previous negative biopsies, PET/MRI is used to test for tumours and target potential following biopsy. We aimed to determine different PSMA PET timing effects on signal kinetics and test its correlation with the patients’ PSA and Gleason scores (GS). Methods A total of 100 patients were examined for 900 s using PET/MRI approximately 1–2 h p.i. depending on the tracer used (68Ga-PSMA-11, 18F-PSMA-1007 or 18F-rhPSMA7). The scans were reconstructed in static and dynamic mode (6 equal frames capturing “late” PSMA dynamics). TACs were computed for detected lesions as well as linear regression plots against time for static (SUV) and dynamic (SUV, SUL, and percent injected dose per gram) parameters. All computed trends were tested for correlation with PSA and GS. Results Static and dynamic scans allowed unchanged lesion detection despite the difference in statistics. For all tracers, the lesions in the pelvic lymph nodes and bones had a mostly negative activity concentration trend (78% and 68%, resp.), while a mostly positive, stronger trend was found for the lesions in the prostate and prostatic fossa following RPE (84% and 83%, resp.). In case of 68Ga-PSMA-11, a strong negative (Rmin = − 0.62, Rmax = − 0.73) correlation was found between the dynamic parameters and the PSA. 18F-PSMA-1007 dynamic data showed no correlation with PSA, while for 18F-rhPSMA7 dynamic data, it was consistently low positive (Rmin = 0.29, Rmax = 0.33). All tracers showed only moderate correlation against GS (Rmin = 0.41, Rmax = 0.48). The static parameters showed weak correlation with PSA (Rmin = 0.24, Rmax = 0.36) and no correlation with GS. Conclusion “Late” dynamic PSMA data provided additional insight into the PSMA kinetics. While a stable moderate correlation was found between the PSMA kinetics in pelvic lesions and GS, a significantly variable correlation with the PSA values was shown depending on the radiotracer used, the highest being consistently for 68Ga-PSMA-11. We reason that with such late dynamics, the PSMA kinetics are relatively stable and imaging could even take place at earlier time points as is now in the clinical routine.