A Comparison of Globally Applied Prognostic Risk Groups and the Prevalence of Metastatic Disease on Prostate-specific Membrane Antigen Positron Emission Tomography in Patients with Newly Diagnosed Prostate Cancer.

BACKGROUND: Various risk classification systems (RCSs) are used globally to stratify newly diagnosed patients with prostate cancer (PCa) into prognostic groups. OBJECTIVE: To compare the predictive value of different prognostic subgroups (low-, intermediate-, and high-risk disease) within the RCSs for detecting metastatic disease on prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/computed tomography (CT) for primary staging, and to assess whether further subdivision of subgroups would be beneficial. DESIGN, SETTING, AND PARTICIPANTS: Patients with newly diagnosed PCa, in whom PSMA-PET/CT was performed between 2017 and 2022, were studied retrospectively. Patients were stratified into risk groups based on four RCSs: European Association of Urology, National Comprehensive Cancer Network (NCCN), Cambridge Prognostic Group (CPG), and Cancer of the Prostate Risk Assessment. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The prevalence of metastatic disease on PSMA-PET/CT was compared among the subgroups within the four RCSs. RESULTS AND LIMITATIONS: In total, 2630 men with newly diagnosed PCa were studied. Any metastatic disease was observed in 35% (931/2630) of patients. Among patients classified as having intermediate- and high-risk disease, the prevalence of metastases ranged from approximately 12% to 46%. Two RCSs further subdivided these groups. According to the NCCN, metastatic disease was observed in 5.8%, 13%, 22%, and 62% for favorable intermediate-, unfavorable intermediate-, high-, and very-high-risk PCa, respectively. Regarding the CPG, these values were 6.9%, 13%, 21%, and 60% for the corresponding risk groups. CONCLUSIONS: This study underlines the importance of nuanced risk stratification, recommending the further subdivision of intermediate- and high-risk disease given the notable variation in the prevalence of metastatic disease. PSMA-PET/CT for primary staging should be reserved for patients with unfavorable intermediate- or higher-risk disease. PATIENT SUMMARY: The use of various risk classification systems in patients with prostate cancer helps identify those at a higher risk of having metastatic disease on prostate-specific membrane antigen positron emission tomography/computed tomography for primary staging.

Optimization and validation of 18F-DCFPyL PET radiomics-based machine learning models in intermediate- to high-risk primary prostate cancer.

INTRODUCTION: Radiomics extracted from prostate-specific membrane antigen (PSMA)-PET modeled with machine learning (ML) may be used for prediction of disease risk. However, validation of previously proposed approaches is lacking. We aimed to optimize and validate ML models based on 18F-DCFPyL-PET radiomics for the prediction of lymph-node involvement (LNI), extracapsular extension (ECE), and postoperative Gleason score (GS) in primary prostate cancer (PCa) patients. METHODS: Patients with intermediate- to high-risk PCa who underwent 18F-DCFPyL-PET/CT before radical prostatectomy with pelvic lymph-node dissection were evaluated. The training dataset included 72 patients, the internal validation dataset 24 patients, and the external validation dataset 27 patients. PSMA-avid intra-prostatic lesions were delineated semi-automatically on PET and 480 radiomics features were extracted. Conventional PET-metrics were derived for comparative analysis. Segmentation, preprocessing, and ML methods were optimized in repeated 5-fold cross-validation (CV) on the training dataset. The trained models were tested on the combined validation dataset. Combat harmonization was applied to external radiomics data. Model performance was assessed using the receiver-operating-characteristics curve (AUC). RESULTS: The CV-AUCs in the training dataset were 0.88, 0.79 and 0.84 for LNI, ECE, and GS, respectively. In the combined validation dataset, the ML models could significantly predict GS with an AUC of 0.78 (p<0.05). However, validation AUCs for LNI and ECE prediction were not significant (0.57 and 0.63, respectively). Conventional PET metrics-based models had comparable AUCs for LNI (0.59, p>0.05) and ECE (0.66, p>0.05), but a lower AUC for GS (0.73, p<0.05). In general, Combat harmonization improved external validation AUCs (-0.03 to +0.18). CONCLUSION: In internal and external validation, 18F-DCFPyL-PET radiomics-based ML models predicted high postoperative GS but not LNI or ECE in intermediate- to high-risk PCa. Therefore, the clinical benefit seems to be limited. These results underline the need for external and/or multicenter validation of PET radiomics-based ML model analyses to assess their generalizability.

The association between clinical, sociodemographic, familial, and environmental factors and treatment resistance in schizophrenia: A machine-learning-based approach.

BACKGROUND: Prediction of treatment resistance in schizophrenia (TRS) would be helpful to reduce the duration of ineffective treatment and avoid delays in clozapine initiation. We applied machine learning to identify clinical, sociodemographic, familial, and environmental variables that are associated with TRS and could potentially predict TRS in the future. STUDY DESIGN: Baseline and follow-up data on trait(-like) variables from the Genetic Risk and Outcome of Psychosis (GROUP) study were used. For the main analysis, we selected patients with non-affective psychotic disorders who met TRS (n = 200) or antipsychotic-responsive criteria (n = 423) throughout the study. For a sensitivity analysis, we only selected patients who met TRS (n = 76) or antipsychotic-responsive criteria (n = 123) at follow-up but not at baseline. Random forest models were trained to predict TRS in both datasets. SHapley Additive exPlanation values were used to examine the variables' contributions to the prediction. STUDY RESULTS: Premorbid functioning, age at onset, and educational degree were most consistently associated with TRS across both analyses. Marital status, current household, intelligence quotient, number of moves, and family loading score for substance abuse also consistently contributed to the prediction of TRS in the main or sensitivity analysis. The diagnostic performance of our models was modest (area under the curve: 0.66-0.69). CONCLUSIONS: We demonstrate that various clinical, sociodemographic, familial, and environmental variables are associated with TRS. Our models only showed modest performance in predicting TRS. Prospective large multi-centre studies are needed to validate our findings and investigate whether the model's performance can be improved by adding data from different modalities.

Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features.

PURPOSE: Biomarkers that can accurately predict outcome in DLBCL patients are urgently needed. Radiomics features extracted from baseline [18F]-FDG PET/CT scans have shown promising results. This study aims to investigate which lesion- and feature-selection approaches/methods resulted in the best prediction of progression after 2 years. METHODS: A total of 296 patients were included. 485 radiomics features (n = 5 conventional PET, n = 22 morphology, n = 50 intensity, n = 408 texture) were extracted for all individual lesions and at patient level, where all lesions were aggregated into one VOI. 18 features quantifying dissemination were extracted at patient level. Several lesion selection approaches were tested (largest or hottest lesion, patient level [all with/without dissemination], maximum or median of all lesions) and compared to the predictive value of our previously published model. Several data reduction methods were applied (principal component analysis, recursive feature elimination (RFE), factor analysis, and univariate selection). The predictive value of all models was tested using a fivefold cross-validation approach with 50 repeats with and without oversampling, yielding the mean cross-validated AUC (CV-AUC). Additionally, the relative importance of individual radiomics features was determined. RESULTS: Models with conventional PET and dissemination features showed the highest predictive value (CV-AUC: 0.72-0.75). Dissemination features had the highest relative importance in these models. No lesion selection approach showed significantly higher predictive value compared to our previous model. Oversampling combined with RFE resulted in highest CV-AUCs. CONCLUSION: Regardless of the applied lesion selection or feature selection approach and feature reduction methods, patient level conventional PET features and dissemination features have the highest predictive value. Trial registration number and date: EudraCT: 2006-005174-42, 01-08-2008.

Targeting PSMA Revolutionizes the Role of Nuclear Medicine in Diagnosis and Treatment of Prostate Cancer.

Targeting the prostate-specific membrane antigen (PSMA) protein has become of great clinical value in prostate cancer (PCa) care. PSMA positron emission tomography/computed tomography (PET/CT) is increasingly used in initial staging and restaging at biochemical recurrence in patients with PCa, where it has shown superior detection rates compared to previous imaging modalities. Apart from targeting PSMA for diagnostic purposes, there is a growing interest in developing ligands to target the PSMA-protein for radioligand therapy (RLT). PSMA-based RLT is a novel treatment that couples a PSMA-antibody to (alpha or beta-emitting) radionuclide, such as Lutetium-177 (177Lu), to deliver high radiation doses to tumor cells locally. Treatment with 177Lu-PSMA RLT has demonstrated a superior overall survival rate within randomized clinical trials as compared to routine clinical care in patients with metastatic castration-resistant prostate cancer (mCRPC). The current review provides an overview of the literature regarding recent developments in nuclear medicine related to PSMA-targeted PET imaging and Theranostics.

Bone Metastases Are Measurable: The Role of Whole-Body MRI and Positron Emission Tomography.

Metastatic tumor deposits in bone marrow elicit differential bone responses that vary with the type of malignancy. This results in either sclerotic, lytic, or mixed bone lesions, which can change in morphology due to treatment effects and/or secondary bone remodeling. Hence, morphological imaging is regarded unsuitable for response assessment of bone metastases and in the current Response Evaluation Criteria In Solid Tumors 1.1 (RECIST1.1) guideline bone metastases are deemed unmeasurable. Nevertheless, the advent of functional and molecular imaging modalities such as whole-body magnetic resonance imaging (WB-MRI) and positron emission tomography (PET) has improved the ability for follow-up of bone metastases, regardless of their morphology. Both these modalities not only have improved sensitivity for visual detection of bone lesions, but also allow for objective measurements of bone lesion characteristics. WB-MRI provides a global assessment of skeletal metastases and for a one-step "all-organ" approach of metastatic disease. Novel MRI techniques include diffusion-weighted imaging (DWI) targeting highly cellular lesions, dynamic contrast-enhanced MRI (DCE-MRI) for quantitative assessment of bone lesion vascularization, and multiparametric MRI (mpMRI) combining anatomical and functional sequences. Recommendations for a homogenization of MRI image acquisitions and generalizable response criteria have been developed. For PET, many metabolic and molecular radiotracers are available, some targeting tumor characteristics not confined to cancer type (e.g. 18F-FDG) while other targeted radiotracers target specific molecular characteristics, such as prostate specific membrane antigen (PSMA) ligands for prostate cancer. Supporting data on quantitative PET analysis regarding repeatability, reproducibility, and harmonization of PET/CT system performance is available. Bone metastases detected on PET and MRI can be quantitatively assessed using validated methodologies, both on a whole-body and individual lesion basis. Both have the advantage of covering not only bone lesions but visceral and nodal lesions as well. Hybrid imaging, combining PET with MRI, may provide complementary parameters on the morphologic, functional, metabolic and molecular level of bone metastases in one examination. For clinical implementation of measuring bone metastases in response assessment using WB-MRI and PET, current RECIST1.1 guidelines need to be adapted. This review summarizes available data and insights into imaging of bone metastases using MRI and PET.

SUVs Are Adequate Measures of Lesional 18F-DCFPyL Uptake in Patients with Low Prostate Cancer Disease Burden.

In prostate cancer (PCa) patients, the tumor-to-blood ratio (TBR) has been validated as the preferred simplified method for lesional 18F-DCFPyL (a radiolabeled prostate-specific membrane antigen ligand) uptake quantification on PET. In contrast to SUVs, the TBR accounts for variability in arterial input functions caused by differences in total tumor burden between patients (the sink effect). However, TBR depends strongly on tracer uptake interval and has worse repeatability and is less applicable in clinical practice than SUVs. We investigated whether SUV could provide adequate quantification of 18F-DCFPyL uptake on PET/CT in a patient cohort with low PCa burden. Methods: In total, 116 patients with PCa undergoing 18F-DCFPyL PET/CT imaging were retrospectively included. All 18F-DCFPyL-avid lesions suspected of being PCa were semiautomatically delineated. SUVpeak was plotted against TBR for the most intense lesion of each patient. The correlation of SUVpeak and TBR was evaluated using linear regression and was stratified for patients undergoing PET/CT for primary staging, patients undergoing restaging at biochemical recurrence, and patients with metastatic castration-resistant PCa. Moreover, the correlation was evaluated as a function of tracer uptake time, prostate-specific antigen level, and PET-positive tumor volume. Results: In total, 436 lesions were delineated (median, 1 per patient; range, 1-66). SUVpeak correlated well with TBR in patients with PCa and a total tumor volume of less than 200 cm3 (R2 = 0.931). The correlation between SUV and TBR was not affected by disease setting, prostate-specific antigen level, or tumor volume. SUVpeak depended less on tracer uptake time than did TBR. Conclusion: For 18F-DCFPyL PET/CT, SUVpeak correlates strongly with TBR. Therefore, it is a valuable simplified, semiquantitative measurement in patients with low-volume PCa (<200 cm3). SUVpeak can therefore be applied in 18F-DCFPyL PET assessment as an imaging biomarker to characterize tumors and to monitor treatment outcomes.

Classification of negative and positive 18F-florbetapir brain PET studies in subjective cognitive decline patients using a convolutional neural network.

PURPOSE: Visual reading of 18F-florbetapir positron emission tomography (PET) scans is used in the diagnostic process of patients with cognitive disorders for assessment of amyloid-ß (Aß) depositions. However, this can be time-consuming, and difficult in case of borderline amyloid pathology. Computer-aided pattern recognition can be helpful in this process but needs to be validated. The aim of this work was to develop, train, validate and test a convolutional neural network (CNN) for discriminating between Aß negative and positive 18F-florbetapir PET scans in patients with subjective cognitive decline (SCD). METHODS: 18F-florbetapir PET images were acquired and visually assessed. The SCD cohort consisted of 133 patients from the SCIENCe cohort and 22 patients from the ADNI database. From the SCIENCe cohort, standardized uptake value ratio (SUVR) images were computed. From the ADNI database, SUVR images were extracted. 2D CNNs (axial, coronal and sagittal) were built to capture features of the scans. The SCIENCe scans were randomly divided into training and validation set (5-fold cross-validation), and the ADNI scans were used as test set. Performance was evaluated based on average accuracy, sensitivity and specificity from the cross-validation. Next, the best performing CNN was evaluated on the test set. RESULTS: The sagittal 2D-CNN classified the SCIENCe scans with the highest average accuracy of 99% ± 2 (SD), sensitivity of 97% ± 7 and specificity of 100%. The ADNI scans were classified with a 95% accuracy, 100% sensitivity and 92.3% specificity. CONCLUSION: The 2D-CNN algorithm can classify Aß negative and positive 18F-florbetapir PET scans with high performance in SCD patients.

Machine learning-based analysis of [18F]DCFPyL PET radiomics for risk stratification in primary prostate cancer.

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.