qPSMA: Semiautomatic Software for Whole-Body Tumor Burden Assessment in Prostate Cancer Using 68Ga-PSMA11 PET/CT

Diagnostic value of 18F-PSMA-1007 PET/CT for predicting the pathological grade of prostate cancer

This study was designed to evaluate the diagnostic efficacy of relevant parameters of 18F-prostate-specific membrane antigen (PSMA)-1007 PET/CT in predicting the pathological grade of primary prostate cancer. Briefly, a prospective analysis was performed on 53 patients diagnosed with prostate cancer by systematic puncture biopsy, followed by 18F-PSMA-1007 PET/CT examination prior to treatment within 10 d. The patients were grouped in accordance with the Gleason grading system revised by the International Association of Urology Pathology (ISUP). They were divided into high-grade group (ISUP 4-5 group) and low-grade group (ISUP 1-3 group). The differences in maximum standardized uptake value (SUVmax), tumor-to-background ratio (TBR), intraprostatic PSMA-derived tumor volume (iPSMA-TV), and intraprostatic total lesion PSMA (iTL-PSMA) between the high- and low-grade group were statistically significant (p < .001). No significant difference was found for mean standardized uptake value (SUVmean) between the high- and low-grade groups (Z =  -1.131, p = .258). Besides, binary multivariate logistic regression analysis showed that only iPSMA-TV and iTL-PSMA were independent predictors of the pathological grading, for which the odds ratios were 18.821 [95% confidence interval (CI): 2.040-173.614, p = .010] and 0.758 (95% CI: 0.613-0.938, p = .011), respectively. The area under the ROC of this regression model was 0.983 (95% CI: 0.958-1.00, p < .001). Only iTL-PSMA was a significant parameter for distinguishing ISUP-4 and ISUP-5 groups (Z =  -2.043, p = .041). In a nutshell, 18F-PSMA-1007 PET/CT has good application value in predicting the histopathological grade of primary prostate cancer. Three-dimensional volume metabolism parameters iPSMA-TV and iTL-PSMA were found to be independent predictors for pathological grade.

Assessing the Heterogeneity of Response of [68Ga] Ga-PSMA-11 PET/CT Lesions in Patients With Biochemical Recurrence of Prostate Cancer

INTRODUCTION

Treatment of men with metastatic prostate cancer can be difficult due to the heterogeneity of response of lesions. [68Ga]Ga-PSMA-11 (PSMA) PET/CT assists with monitoring and directing clinical intervention; however, the impact of response heterogeneity has yet to be related to outcome measures. The aim of this study was to assess the impact of quantitative imaging information on the value of PSMA PET/CT to assess patient outcomes in response evaluation.

PATIENTS AND METHODS

Baseline and follow-up (6 months) PSMA PET/CT of 162 men with oligometastatic PC treated with standard clinical care were acquired between 2015 and 2016 for analysis. An augmentative software medical device was used to track lesions between scans and quantify lesion change to categorize them as either new, increasing, stable, decreasing, or disappeared. Quantitative imaging features describing the size, intensity, extent, change, and heterogeneity of change (based on percent change in SUVtotal) among lesions were extracted and evaluated for association with overall survival (OS) using Cox regression models. Model performance was evaluated using the c-index.

RESULTS

Forty-one (25%) of subjects demonstrated heterogeneous response at follow-up, defined as having at least 1 new or increasing lesion and at least 1 decreasing or disappeared lesion. Subjects with heterogeneous response demonstrated significantly shorter OS than subjects without (median OS = 76.6 months vs. median OS not reached, P < .05, c-index = 0.61). In univariate analyses, SUVtotal at follow-up was most strongly associated with OS (HR = 1.29 [1.19, 1.40], P < .001, c-index = 0.73). Multivariable models applied using heterogeneity of change features demonstrated higher performance (c-index = 0.79) than models without (c-index = 0.71-0.76, P < .05).

CONCLUSION

Augmentative software tools enhance the evaluation change on serial PSMA PET scans and can facilitate lesional evaluation between timepoints. This study demonstrates that a heterogeneous response at a lesional level may impact adversely on patient outcomes and supports further investigation to evaluate the role of imaging to guide individualized patient management to improve clinical outcomes.

Prostate-specific Membrane Antigen: Interpretation Criteria, Standardized Reporting, and the Use of Machine Learning

Prostate-specific membrane antigen targeting positron emission tomography (PSMA-PET) is routinely used for the staging and restaging of patients with various stages of prostate cancer. For clear communication with referring physicians and to improve inter-reader agreement, the use of standardized reporting templates is mandatory. Increasingly, tumor volume is used by reporting and response assessment frameworks to prognosticate patient outcome or measure response to therapy. However, the quantification of tumor volume is often too time-consuming in routine clinical practice. Machine learning-based tools can facilitate the quantification of tumor volume for improved outcome prognostication.

Prostate Cancer Theranostics With 177Lu-PSMA

This review paper highlights the transformative role of PSMA-targeted diagnostics and therapy in prostate cancer management, particularly focusing on 177Lu-PSMA-617, approved by the FDA and EMA for metastatic castration-resistant prostate cancer (mCRPC) patients post-chemotherapy and ARPI treatment. Originating from the VISION trial's success, this paper navigates the current radioligand therapy (RLT) indications, emphasizing practical patient selection, planning, and treatment execution. It critically examines Lu-PSMA's comparative effectiveness against cabazitaxel and Ra-223, addressing decision-making dilemmas for mCRPC treatments. Furthermore, the paper discusses Lu-PSMA in chemotherapy-naïve patients and its application in hormone-sensitive prostate cancer, underlined by ongoing global studies. A significant concern is Lu-PSMA's long-term safety profile, particularly nephrotoxicity risks, necessitating further investigation. The possibility of Lu-PSMA rechallenge in responsive patients is explored, stressing the need for comprehensive analyses and real-world data to refine treatment protocols. Conclusively, PSMA-targeted therapy marks a significant advance in prostate cancer therapy, advocating for its integration into a multimodal, patient-centric treatment approach. The review underscores the imperative for additional comparative studies to optimize treatment sequences and outcomes, ultimately enhancing long-term prognosis and disease control in prostate cancer management.

Whole-body tumour burden on [18F]DCFPyL PET/CT in biochemical recurrence of prostate cancer: association with tumour biology and PSA kinetics

PURPOSE

The objective was to assess the association between molecular imaging (mi) variables on [18F]DCFPyL-PET/CT with clinical and disease characteristics and prostate specific antigen (PSA) related variables in patients with biochemical recurrence of prostate cancer (BRPC).

MATERIAL AND METHODS

We analysed patients with BRPC after radical treatment. We obtained clinical and PSA variables: International Society of Urology Pathology (ISUP) grade group, European Association of Urology (EAU) risk classification, PSA (PSA≤1ng/ml, 12), PSA doubling time (PSAdt) and PSA velocity (PSAvel). All PET/CT scans were reviewed with the assistance of automated Prostate Molecular Imaging Standardized Evaluation (aPROMISE) software and lesions' segmentation in positive scans was performed using this platform. Standardized uptake value (SUV) derived variables; tumour burden variables [whole-body tumour volume (wbTV), whole-body tumour lesion activity (wbTLA) and whole-body mi PSMA (wbPSMA)] and miTNM staging were obtained. Cut-off of PSA and kinetics able to predict PET/CT results were obtained. Associations between disease and mi variables were analysed using ANOVA, Kruskal-Wallis and Spearman's correlation tests. Multivariate analysis was also performed.

RESULTS

Two hundred and seventy-five patients were studied. [18F]DCFPyL-PET/CT were positive in 165/275 patients. In multivariate analysis, moment of biochemical recurrence, ISUP group, PSA level and PSAvel showed significant association with the detection rate. miTNM showed significant association with PSA level (p<0.001) and kinetics (p<0.001), being higher in patients with metastatic disease. Both PSA and PSAvel showed moderate correlation with wbTV, wbTLA and wbPSMA (p<0.001). A weak correlation with SUVs was found. Mean wbTV, wbTLA and wbPSMA values were significantly higher in PSA > 2ng/ml, PSAdt ≤ 6 months and PSAvel ≥ 0.2ng/ml/month groups. Also, wbTV (p=0.039) and wbPSMA (p=0.020) were significantly higher in patients with ISUP grade group 5. PSA and PSAvel cut-offs (1.15 ng/ml and 0.065 ng/ml/month) were significantly associated with a positive PET/CT.

CONCLUSION

Higher PSA values, unfavourable PSA kinetics and ISUP grade group 5 were robust predictive variables of larger tumour burden variables on [18F]DCFPyL PET/CT assessed by aPROMISE platform.

Treatment Response Imaging in Prostate Cancer

Objective criteria for measuring treatment response in prostate cancer are critical to clinical research and practice. The Prostate Cancer Working Group 3 criteria are widely accepted relying only on conventional imaging for radiographic treatment response. Prostate-specific membrane antigen PET/computed tomography was proven to be superior to conventional imaging in initial diagnosis and biochemical recurrence of prostate cancer. Moreover, there is growing evidence of its role in treatment response assessment in prostate cancer. This study will review the different criteria for imaging treatment response on conventional and advanced molecular imaging for different therapies, and the future perspective in posttherapy imaging.

PSMA-PET follow-up to assess response in patients not receiving PSMA therapy: Is there value beyond localization of disease?

Introduction: Prostate Specific Membrane Antigen Positron Emission Tomography (PSMA-PET) is routinely used for the staging of patients with prostate cancer, but data on response assessment are sparse and primarily stem from metastatic castration-resistant prostate cancer (mCRPC) patients treated with PSMA radioligand therapy. Still, follow-up PSMA-PET is employed in earlier disease stages in case of clinical suspicion of disease persistence, recurrence or progression to decide if localized or systemic treatment is indicated. Therefore, the prognostic value of PSMA-PET derived tumor volumes in earlier disease stages (i.e., hormone-sensitive prostate cancer (HSPC) and non-[177Lu]Lu-PSMA-617 (LuPSMA) therapy castration resistant prostate cancer (CRPC)) are evaluated in this manuscript. Methods: A total number of 73 patients (6 primary staging, 42 HSPC, 25 CRPC) underwent two (i.e., baseline and follow-up, median interval: 379 days) whole-body [68Ga]Ga-PSMA-11 PET/CT scans between Nov 2014 and Dec 2018. Analysis was restricted to non-LuPSMA therapy patients. PSMA-PETs were retrospectively analyzed and primary tumor, lymph node-, visceral-, and bone metastases were segmented. Body weight-adjusted organ-specific and total tumor volumes (PSMAvol: sum of PET volumes of all lesions) were measured for baseline and follow-up. PSMAvol response was calculated as the absolute difference of whole-body tumor volumes. High metastatic burden (>5 metastases), RECIP 1.0 and PSMA-PET Progression Criteria (PPP) were determined. Survival data were sourced from the cancer registry. Results: The average number of tumor lesions per patient on the initial PET examination was 10.3 (SD 28.4). At baseline, PSMAvol was strongly associated with OS (HR 3.92, p <0.001; n = 73). Likewise, response in PSMAvol was significantly associated with OS (HR 10.48, p < 0.005; n = 73). PPP achieved significance as well (HR 2.19, p <0.05, n = 73). Patients with hormone sensitive disease and poor PSMAvol response (upper quartile of PSMAvol change) in follow-up had shorter outcome (p < 0.05; n = 42). PSMAvol in bones was the most relevant parameter for OS prognostication at baseline and for response assessment (HR 31.11 p < 0.001; HR 32.27, p < 0.001; n = 73). Conclusion: PPP and response in PSMAvol were significantly associated with OS in the present heterogeneous cohort. Bone tumor volume was the relevant miTNM region for OS prognostication. Future prospective evaluation of the performance of organ specific PSMAvol in more homogeneous cohorts seems warranted.

RECIP 1.0 Predicts Progression-Free Survival After [177Lu]Lu-PSMA Radiopharmaceutical Therapy in Patients with Metastatic Castration-Resistant Prostate Cancer

Response Evaluation Criteria in Prostate-Specific Membrane Antigen Imaging (RECIP) 1.0 is an evidence-based framework to evaluate therapeutic efficacy in metastatic prostate cancer using prostate-specific membrane antigen (PSMA) PET/CT. This study aimed to evaluate the associations of interim PSMA PET/CT by RECIP 1.0 with short-term outcome after radiopharmaceutical treatment. Methods: This multicenter retrospective study included patients with metastatic castration-resistant prostate cancer who underwent [177Lu]Lu-PSMA radiopharmaceutical therapy at 3 academic centers and received PSMA PET/CT at baseline and at 12 wk. Pairs of PSMA PET/CT images were assessed by 5 readers for visual RECIP 1.0. The primary outcome was the association of RECIP with prostate-specific antigen progression-free survival (PSA-PFS) by Kaplan-Meier analysis. Results: In total, 124 of 287 screened patients met the inclusion criteria, with 0 (0%), 29 (23%), 54 (44%), and 41 (33%) of those 124 patients having complete response, partial response, stable disease, or progressive disease (PD) by visual RECIP 1.0, respectively. Patients with visual RECIP PD had a significantly shorter PSA-PFS than those with RECIP stable disease or with RECIP partial response (2.6 vs. 6.4 vs. 8.4 mo; P < 0.001). The median PSA-PFS among patients with RECIP PD versus those with non-RECIP PD was 2.6 versus 7.2 mo (hazard ratio, 13.0; 95% CI, 7.0-24.1; P < 0.001). Conclusion: PSMA PET/CT by RECIP 1.0 after 2 cycles of [177Lu]Lu-PSMA is prognostic for PSA-PFS. PSMA PET/CT by RECIP 1.0 may be used in earlier stages of prostate cancer to evaluate drug efficacy and to predict progression-free survival.

Prostate-specific Membrane Antigen Positron Emission Tomography-detected Disease Extent and Overall Survival of Patients with High-risk Nonmetastatic Castration-resistant Prostate Cancer: An International Multicenter Retrospective Study

Previously, we demonstrated that prostate-specific membrane antigen positron emission tomography (PSMA-PET) revealed distant metastases in 109/200 patients (39% distant nodes, 24% bone, and 6% visceral organ) with nonmetastatic castration-resistant prostate cancer (nmCRPC) and high-risk features (International Society of Urological Pathology score ≥4 and/or prostate-specific antigen doubling time ≤10 mo) without metastases by conventional imaging. However, the impact of disease extent determined by PSMA-PET on patient outcomes is unknown. We followed these 200 patients for a median of 43 mo after PSMA-PET and retrospectively assessed the association between patient characteristics, PSMA-PET findings, treatment management, and outcomes using a Kaplan-Meier model and Cox multivariable regressions. Among assessed disease characteristics, polymetastatic disease (five or more distant lesions on PET) was independently associated with shorter overall survival (OS; median 61 mo vs not reached; hazard ratio [95% confidence interval], 1.81 [1.00-3.27]; p = 0.050) and time to new metastases (median 38 vs 60 mo; 1.80 [1.10-2.96]; p = 0.019), and initial pN1 status with shorter OS (55 mo vs not reached; 1.94 [1.12-3.37]; p = 0.019). Following PSMA-PET, locoregional salvage therapies were used most commonly in no/local disease (58%), and androgen receptor signaling inhibitors were used in distant metastatic disease (51%). PSMA-PET provides additional risk stratification for patients with nmCRPC. Polymetastatic disease (five or more distant lesions) is associated with worse outcomes. PATIENT SUMMARY: A novel sensitive imaging technology, called prostate-specific membrane antigen positron emission tomography (PSMA-PET), allows doctors to detect the spread of prostate cancer, known as distant metastases, earlier and more accurately than in the past. In our study, PSMA-PET detected none to many metastases in patients who were considered free of distant metastasis by conventional imaging. These findings predicted outcomes and were used to select appropriate treatment.

PSMA-Targeted Radiopharmaceuticals for Prostate Cancer Diagnosis and Therapy

ABSTRACT

Prostate cancer (PCa) is the most common noncutaneous malignancy in men. Until recent years, accurate imaging of men with newly diagnosed PCa, or recurrent or low-volume metastatic disease, was limited. Further, therapeutic options for men with advanced, metastatic, castration-resistant disease were increasingly limited as a result of increasing numbers of systemic therapies being combined in the upfront metastatic setting. The advent of urea-based, small-molecule inhibitors of prostate-specific membrane antigen (PSMA) has partially addressed those shortcomings in diagnosis and therapy of PCa. On the diagnostic side, there are multiple pivotal phase III trials with several different agents having demonstrated utility in the initial staging setting, with generally modest sensitivity but very high specificity for determining otherwise-occult pelvic nodal involvement. That latter statistic drives the utility of the scan by allowing imaging interpreters to read with very high sensitivity while maintaining a robust specificity. Other pivotal phase III trials have demonstrated high detection efficiency in patients with biochemical failure, with high positive predictive value at the lesion level, opening up possible new avenues of therapy such as metastasis-directed therapy. Beyond the diagnostic aspects of PSMA-targeted radiotracers, the same urea-based chemical scaffolds can be altered to deliver therapeutic isotopes to PCa cells that express PSMA. To date, one such agent, when combined with best standard-of-care therapy, has demonstrated an ability to improve overall survival, progression-free survival, and freedom from skeletal events relative to best standard-of-care therapy alone in men with metastatic, castration-resistant PCa who are post chemotherapy. Within the current milieu, there are a number of important future directions including the use of artificial intelligence to better leverage diagnostic findings, further medicinal chemistry refinements to the urea-based structure that may allow improved tumor targeting and decreased toxicities, and the incorporation of new radionuclides that may better balance efficacy with toxicities than those nuclides that are available.

An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer

Uptake segmentation and classification on PSMA PET/CT are important for automating whole-body tumor burden determinations. We developed and evaluated an automated deep learning (DL)-based framework that segments and classifies uptake on PSMA PET/CT. We identified 193 [18F] DCFPyL PET/CT scans of patients with biochemically recurrent prostate cancer from two institutions, including 137 [18F] DCFPyL PET/CT scans for training and internally testing, and 56 scans from another institution for external testing. Two radiologists segmented and labelled foci as suspicious or non-suspicious for malignancy. A DL-based segmentation was developed with two independent CNNs. An anatomical prior guidance was applied to make the DL framework focus on PSMA-avid lesions. Segmentation performance was evaluated by Dice, IoU, precision, and recall. Classification model was constructed with multi-modal decision fusion framework evaluated by accuracy, AUC, F1 score, precision, and recall. Automatic segmentation of suspicious lesions was improved under prior guidance, with mean Dice, IoU, precision, and recall of 0.700, 0.566, 0.809, and 0.660 on the internal test set and 0.680, 0.548, 0.749, and 0.740 on the external test set. Our multi-modal decision fusion framework outperformed single-modal and multi-modal CNNs with accuracy, AUC, F1 score, precision, and recall of 0.764, 0.863, 0.844, 0.841, and 0.847 in distinguishing suspicious and non-suspicious foci on the internal test set and 0.796, 0.851, 0.865, 0.814, and 0.923 on the external test set. DL-based lesion segmentation on PSMA PET is facilitated through our anatomical prior guidance strategy. Our classification framework differentiates suspicious foci from those not suspicious for cancer with good accuracy.

Pre-treatment 68 Ga-PSMA-11 PET/CT Prognostic Value in Predicting Response to 177Lu-PSMA-I&T Therapy and Patient Survival

PURPOSE

To assess the prognostic value of pre-treatment [68Ga]Ga-PSMA-11 PET/CT and other baseline clinical characteristics in predicting prostate cancer (PCa) patients response to [177Lu]Lu-PSMA (PSMA-I&T), as well as patient survival.

PROCEDURES

In this retrospective study, 81 patients who received [177Lu]Lu-PSMA-I&T between October 2018 and January 2023 were reviewed. Eligible patients had metastatic castration-resistant PCa, underwent pre-treatment [68Ga]Ga-PSMA-11 PET/CT, and had serum prostate-specific antigen (PSA) levels available. On PET/CT images, SUVmax, SULmax, SUVpeak, and SULpeak of the most-avid tumoral lesion, as well as SUVmean of the parotid gland (P-SUVmean) and liver (L-SUVmean), were measured. Also, whole-body PSMA tumour volume (PSMA-TV) and total lesion PSMA (TL-PSMA) were calculated. To interpret treatment response after [177Lu]Lu-PSMA-I&T, a composite of PSA values and [68Ga]Ga-PSMA-11 PET/CT findings were considered. The outcomes were dichotomised into progressive versus controlled (stable disease or partial response) disease. Then, the association of baseline parameters with patient response was evaluated. Also, survival analyses were performed to assess baseline parameters in predicting overall survival.

RESULTS

Sixty patients (age:73 ± 8, PSA:185 ± 371) were included. Patients received at least one cycle of [177Lu]Lu-PSMA therapy (median = 4). Overall, half of the patients showed disease progression. In the progressive versus controlled disease evaluation, the highest SULmax, as well as SUVmax and SULmax to both backgrounds (L-SUVmean and P-SUVmean), were significantly correlated with the outcome (p-values < 0.05). In the multivariate analysis, only SULmax to the L-SUVmean remained significant (p-value = 0.038). The best cut-off was 8 (AUC = 0.71). With a median follow-up of 360 days, 11 mortal events were documented. In the multivariate survival analysis, only SULmax to P-SUVmean (cut-off = 2.4; p-value = 0.043) retained significance (hazard ratio = 4.0).

CONCLUSIONS

A greater level of PSMA uptake, specifically higher tumour-to-background uptake in the hottest lesion, may hold substantial prognostic significance, considering both [177Lu]Lu-PSMA-I&T response and patient survival. These ratios may have the potential to be used for PCa patient selection for radioligand therapy.

A convolutional neural network-based system for fully automatic segmentation of whole-body [68Ga]Ga-PSMA PET images in prostate cancer

PURPOSE

The aim of this study was development and evaluation of a fully automated tool for the detection and segmentation of mPCa lesions in whole-body [68Ga]Ga-PSMA-11 PET scans by using a nnU-Net framework.

METHODS

In this multicenter study, a cohort of 412 patients from three different center with all indication of PCa who underwent [68Ga]Ga-PSMA-11 PET/CT were enrolled. Two hundred cases of center 1 dataset were used for training the model. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework. A subset of center 1 dataset and cases of center 2 and center 3 were used for testing of model. The performance of the segmentation pipeline that was developed was evaluated by comparing the fully automatic segmentation mask with the manual segmentation of the corresponding internal and external test sets in three levels including patient-level scan classification, lesion-level detection, and voxel-level segmentation. In addition, for comparison of PET-derived quantitative biomarkers between automated and manual segmentation, whole-body PSMA tumor volume (PSMA-TV) and total lesions PSMA uptake (TL-PSMA) were calculated.

RESULTS

In terms of patient-level classification, the model achieved an accuracy of 83%, sensitivity of 92%, PPV of 77%, and NPV of 91% for the internal testing set. For lesion-level detection, the model achieved an accuracy of 87-94%, sensitivity of 88-95%, PPV of 98-100%, and F1-score of 93-97% for all testing sets. For voxel-level segmentation, the automated method achieved average values of 65-70% for DSC, 72-79% for PPV, 53-58% for IoU, and 62-73% for sensitivity in all testing sets. In the evaluation of volumetric parameters, there was a strong correlation between the manual and automated measurements of PSMA-TV and TL-PSMA for all centers.

CONCLUSIONS

The deep learning networks presented here offer promising solutions for automatically segmenting malignant lesions in prostate cancer patients using [68Ga]Ga-PSMA PET. These networks achieve a high level of accuracy in whole-body segmentation, as measured by the DSC and PPV at the voxel level. The resulting segmentations can be used for extraction of PET-derived quantitative biomarkers and utilized for treatment response assessment and radiomic studies.

Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR

BACKGROUND

Prostate-specific membrane antigen (PSMA) PET/CT imaging is widely used for quantitative image analysis, especially in radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC). Unknown features influencing PSMA biodistribution can be explored by analyzing segmented organs at risk (OAR) and lesions. Manual segmentation is time-consuming and labor-intensive, so automated segmentation methods are desirable. Training deep-learning segmentation models is challenging due to the scarcity of high-quality annotated images. Addressing this, we developed shifted windows UNEt TRansformers (Swin UNETR) for fully automated segmentation. Within a self-supervised framework, the model's encoder was pre-trained on unlabeled data. The entire model was fine-tuned, including its decoder, using labeled data.

METHODS

In this work, 752 whole-body [68Ga]Ga-PSMA-11 PET/CT images were collected from two centers. For self-supervised model pre-training, 652 unlabeled images were employed. The remaining 100 images were manually labeled for supervised training. In the supervised training phase, 5-fold cross-validation was used with 64 images for model training and 16 for validation, from one center. For testing, 20 hold-out images, evenly distributed between two centers, were used. Image segmentation and quantification metrics were evaluated on the test set compared to the ground-truth segmentation conducted by a nuclear medicine physician.

RESULTS

The model generates high-quality OARs and lesion segmentation in lesion-positive cases, including mCRPC. The results show that self-supervised pre-training significantly improved the average dice similarity coefficient (DSC) for all classes by about 3%. Compared to nnU-Net, a well-established model in medical image segmentation, our approach outperformed with a 5% higher DSC. This improvement was attributed to our model's combined use of self-supervised pre-training and supervised fine-tuning, specifically when applied to PET/CT input. Our best model had the lowest DSC for lesions at 0.68 and the highest for liver at 0.95.

CONCLUSIONS

We developed a state-of-the-art neural network using self-supervised pre-training on whole-body [68Ga]Ga-PSMA-11 PET/CT images, followed by fine-tuning on a limited set of annotated images. The model generates high-quality OARs and lesion segmentation for PSMA image analysis. The generalizable model holds potential for various clinical applications, including enhanced RLT and patient-specific internal dosimetry.

PSMA PET/CT for Response Assessment of 177Lu-PSMA Therapy

Prostate-specific membrane antigen (PSMA) PET/CT has been widely integrated into the management of prostate cancer (PCa) patients with biochemical recurrence, is increasingly used for initial staging in high-risk patients prior to surgery or to identify candidates for PSMA-targeted radioligand therapy (RLT). To date, monitoring response in PCa patients in prospective studies remains the domain of conventional imaging, such as magnetic resonance/CT or bone scintigraphy. With the increasing use of PSMA-targeted PET/CT in PCa, however, varying criteria based on molecular imaging have been established to define progressive disease, including "PSMA PET Progression Criteria," "Response evaluation criteria in PSMA PET/CT (RECIP 1.0)" or consensus statements of respective societies. In the present review, we will discuss the current status of PSMA PET/CT for response monitoring, focusing on PSMA RLT with [177Lu]Lu-labeled PSMA ligands, along with a head-to-head comparison of recently published response criteria.

Standardized PSMA-PET Imaging of Advanced Prostate Cancer

Imaging of advanced prostate cancer is a challenging task, as it requires longitudinal characterization of disease extent in a standardized way to enable appropriate treatment selection and evaluation of treatment efficacy. In the last years, prostate-specific membrane antigen (PSMA)-PET/CT has become the reference standard examination for patients with advanced prostate cancer. Together with the rise of PSMA-PET, standardized frameworks for the reporting of image findings have been proposed, eg, the Prostate Cancer Molecular Imaging Standardized Evaluation (PROMISE) and the structured reporting system for PSMA targeted PET imaging (PSMA-RADS) framework. Therefore, recent evidence on PSMA-PET derived tumor volume as useful a biomarker for outcome prognostication and related frameworks will be discussed in the article. The PROMISE framework recommends quantifying the tumor volume per-organ system, which accounts for the fact that the location of the metastases greatly influence its biological aggressiveness. In addition, changes in PSMA-PET derived tumor volume have been shown to be promising biomarkers for response assessment. Limitations of PSMA-PET will also be discussed because the tumor volume might not always be suited for response assessment. As a pitfall of PSMA-based systems, decreasing PSMA-expression might erroneously be interpreted as response to therapy. Also, especially for patients with limited disease, the tumor volume might not be ideal for response assessment. Therefore, various frameworks have been introduced to objectively measure response to therapy with PSMA-PET. Amongst these, the PSMA-PET progression (PPP) criteria and the response evaluation criteria in PSMA (RECIP) are optimized for earlier and later phenotypes of advanced prostate cancer, respectively. Variables needed to determine PPP or RECIP outcome on PSMA-PET are recorded under the umbrella of PROMISE recommendations. In this article, various reporting and response assessment frameworks are explained and discussed. Also, recent evidence for the relevance of PSMA-PET biomarkers for clinical management and outcome prognostication are shown.

Comparative Analysis of Morphological and Functional Effects of 225Ac- and 177Lu-PSMA Radioligand Therapies (RLTs) on Salivary Glands

Most Prostate Specific Membrane Antigens (PSMAs) targeting small molecules accumulate in the salivary glands (SGs), raising concerns about SG toxicity, especially after repeated therapies or therapy with 225Ac-labeled ligands. SG toxicity is assessed clinically by the severity of patient-reported xerostomia, but this parameter can be challenging to objectively quantify. Therefore, we explored the feasibility of using SG volume as a biomarker for toxicity. In 21 patients with late-stage metastatic resistant prostate cancer (mCRPC), the PSMA volume and ligand uptake of SG were analyzed retrospectively before and after two cycles of 177Lu-PSMA (LuPSMA; cohort A) and before and after one cycle of 225Ac-PSMA-617 (AcPSMA, cohort B). Mean Volume-SG in cohort A was 59 ± 13 vs. 54 ± 16 mL (-10%, p = 0.4), and in cohort B, it was 50 ± 13 vs. 40 ± 11 mL (-20%, p = 0.007), respectively. A statistically significant decrease in the activity concentration in the SG was only observed in group B (SUVmean: 9.2 ± 2.8 vs. 5.3 ± 1.8, p < 0.0001; vs. A: SUVmean: 11.2 ± 3.3 vs. 11.1 ± 3.5, p = 0.8). SG volume and PSMA-ligand uptake are promising markers to monitor the SG toxicity after a PSMA RLT.

Prognostic Value of End-of-Treatment PSMA PET/CT in Patients Treated with 177Lu-PSMA Radioligand Therapy: A Retrospective, Single-Center Analysis

Our objective was to evaluate the prognostic value of end-of-treatment prostate-specific membrane antigen (PSMA) PET/CT (PSMA-PET) in patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177Lu-PSMA radioligand therapy (PSMA-RLT). Methods: This was a single-center retrospective study. mCRPC patients who underwent PSMA-RLT with available baseline PSMA-PET (bPET) and end-of-treatment PSMA-PET (ePET) within 6 mo of the last PSMA-RLT cycle were eligible. Overall survival (OS) and prostate-specific antigen (PSA) progression status at the time of ePET (by Prostate Cancer Clinical Trials Working Group 3 criteria) were collected. PSMA-PET tumor segmentation was performed to obtain whole-body PSMA tumor volume (PSMA-VOL) and define progressive (≥20% increase) versus nonprogressive disease. Pairs of bPET and ePET were interpreted for appearance of new lesions. Response Evaluation Criteria in PSMA-PET/CT (RECIP) 1.0 were also applied to define progressive versus nonprogressive disease. The associations between changes in PSMA-VOL, new lesions, RECIP 1.0, and PSA progression status at the time of ePET with OS were evaluated by Kaplan-Meier analysis. Results: Twenty mCRPC patients were included. The median number of treatment cycles was 3.5 (interquartile range [IQR], 2-4). The median time between bPET and cycle 1 of PSMA-RLT was 1.0 mo (IQR, 0.7-1.8 mo). The median time between the last cycle of PSMA-RLT and ePET was 1.9 mo (IQR, 1.2-3.5 mo). Twelve of 20 patients (60%) had died at the last follow-up. The median follow-up time from ePET for survivors was 31.2 mo (IQR, 6.8-40.7 mo). The median OS from ePET was 11.4 mo (IQR, 6.8-30.7 mo). Patients with new lesions on ePET had shorter OS than those without new lesions (median OS, 10.7 mo [95% CI, 9.2-12.2] vs. not reached; P = 0.002). Patients with progressive PSMA-VOL had shorter OS than those with nonprogressive PSMA-VOL (median OS, 10.7 mo [95% CI: 9.7-11.7 mo] vs. not reached; P = 0.007). Patients with progressive RECIP had shorter OS than those with nonprogressive RECIP (median OS, 10.7 mo [95% CI, 9.7-11.7 mo] vs. not reached; P = 0.007). PSA progression at the time of ePET was associated with shorter OS (median, 10.9 mo [95% CI, 9.4-12.4 mo] vs. not reached; P = 0.028). Conclusion: In this retrospective study of 20 mCRPC patients treated with PSMA-RLT, progression on ePET by the appearance of new lesions, changes in PSMA-VOL, and RECIP 1.0 was prognostic for OS. Validation in larger, prospective multicentric clinical trials is warranted.

Prognostic utility of RECIP 1.0 with manual and AI-based segmentations in biochemically recurrent prostate cancer from [68Ga]Ga-PSMA-11 PET images

PURPOSE

This study aimed to (i) validate the Response Evaluation Criteria in PSMA (RECIP 1.0) criteria in a cohort of biochemically recurrent (BCR) prostate cancer (PCa) patients and (ii) determine if this classification could be performed fully automatically using a trained artificial intelligence (AI) model.

METHODS

One hundred ninety-nine patients were imaged with [68Ga]Ga-PSMA-11 PET/CT once at the time of biochemical recurrence and then a second time a median of 6.0 months later to assess disease progression. Standard-of-care treatments were administered to patients in the interim. Whole-body tumour volume was quantified semi-automatically (TTVman) in all patients and using a novel AI method (TTVAI) in a subset (n = 74, the remainder were used in the training process of the model). Patients were classified as having progressive disease (RECIP-PD), or non-progressive disease (non RECIP-PD). Association of RECIP classifications with patient overall survival (OS) was assessed using the Kaplan-Meier method with the log rank test and univariate Cox regression analysis with derivation of hazard ratios (HRs). Concordance of manual and AI response classifications was evaluated using the Cohen's kappa statistic.

RESULTS

Twenty-six patients (26/199 = 13.1%) presented with RECIP-PD according to semi-automated delineations, which was associated with a significantly lower survival probability (log rank p < 0.005) and higher risk of death (HR = 3.78 (1.96-7.28), p < 0.005). Twelve patients (12/74 = 16.2%) presented with RECIP-PD according to AI-based segmentations, which was also associated with a significantly lower survival (log rank p = 0.013) and higher risk of death (HR = 3.75 (1.23-11.47), p = 0.02). Overall, semi-automated and AI-based RECIP classifications were in fair agreement (Cohen's k = 0.31).

CONCLUSION

RECIP 1.0 was demonstrated to be prognostic in a BCR PCa population and is robust to two different segmentation methods, including a novel AI-based method. RECIP 1.0 can be used to assess disease progression in PCa patients with less advanced disease. This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

Effects of novel androgen receptor signaling inhibitors on PSMA PET signal intensity in patients with castrate-resistant prostate cancer: a prospective exploratory serial imaging study

BACKGROUND

PSMA expression is influenced by hormonal status. We evaluated changes in PSA and whole-body 68Ga-PSMA-11 PET/CT (WB-PSMA PET) after initiation of androgen receptor signaling inhibitors (ARSi).

METHODS

Prospectively enrolled patients with metastatic castration-resistant prostate cancer (mCRPC) initiating ARSi underwent serial PSA measurements and WB-PSMA PET at baseline, 1-week, and 3-months post-ARSi. We correlated WB-PSMA PET metrics and PSA kinetics after ARSi to 1-year clinical outcome.

RESULTS

Due to low enrollment rate, the study was closed before reaching the recruitment goal of 30 patients. Nine patients were enrolled. At 1-year, unfavorable outcome was documented in 6/9 (66%) patients. Nine/9 patients completed PSMA PET at 1-week, 5/9 at 3-months. Changes in PSA, PSMA-VOL, SUVmean and SUVmax were - 12%, + 5%, + 3%, and + 10% at 1-week, - 42%, - 16%, - 15% and - 17% at 3-months, respectively.

CONCLUSIONS

Our prospective trial involving 9 mCRPC patients initiating ARSi did not show significant modulation of PSMA expression measured on WB-PSMA PET at 1-week. This study was registered on clinicaltrials.gov (NCT04279561).

Associations of quantitative whole-body PSMA-PET metrics with PSA progression status under long-term androgen deprivation therapy in prostate cancer patients: a retrospective single-center study

PURPOSE

To evaluate whether quantitative whole-body (WB) PSMA-PET metrics under long-term androgen deprivation therapy (ADT) and/or androgen receptor signaling inhibitors (ARSi) are associated with PSA progression.

METHODS

Patients who underwent at least 2 68Ga-PSMA-11 PET/CT scans between October 2016 and April 2021 (n = 372) and started a new line of ADT ± ARSi between PET1 and PET2 were retrospectively screened for inclusion. We investigated the association between PCWG3-defined PSA progression status at PET2 and the following PSMA-PET parameters: appearance of new lesions on PET2, ≥ 20% increase in WB-PSMA tumor volume (WB-PSMA-VOL), progression of disease (PD) by RECIP 1.0, and ≥ 30% increase in WB-PSMA-SUVmean from PET1 to PET2. Spearman's rank correlation coefficients and Fisher's exact test were used to evaluate the associations.

RESULTS

Thirty-five patients were included: 12/35 (34%) were treated with ADT only and 23/35 (66%) with ARSi ± ADT. The median time between PET1 and PET2 was 539 days. Changes (%) in median PSA levels, WB-PSMA-SUVmean, and WB-PSMA-VOL from PET1 to PET2 were -86%, -23%, and -86%, respectively. WB-PSMA-VOL ≥ 20%, new lesions, RECIP-PD, and WB-PSMA-SUVmean ≥ 30% were observed in 5/35 (14%), 9/35 (26%), 5/35 (14%), and 4/35 (11%) of the whole cohort, in 3/9 (33%), 7/9 (78%), 3/9 (33%), and 2/9 (22%) of patients with PSA progression at PET2, and in 2/26 (8%), 2/26 (8%), 2/26 (8%), and 2/26 (8%) of patients without PSA progression at PET2 (p = 0.058, p < 0.001, p = 0.058, p = 0.238, respectively). Changes in PSA were correlated to percent changes in WB-PSMA-VOL and WB-PSMA-SUVmean (Spearman ρ: 0.765 and 0.633, respectively; p < 0.001).

CONCLUSION

Changes in PSA correlated with changes observed on PSMA-PET, although discordance between PSA and PSMA-PET changes was observed. Further research is necessary to evaluate if PSMA-PET parameters can predict progression-free survival and overall survival and serve as novel endpoints in clinical trials.

Artificial Intelligence in Oncological Hybrid Imaging

BACKGROUND

 Artificial intelligence (AI) applications have become increasingly relevant across a broad spectrum of settings in medical imaging. Due to the large amount of imaging data that is generated in oncological hybrid imaging, AI applications are desirable for lesion detection and characterization in primary staging, therapy monitoring, and recurrence detection. Given the rapid developments in machine learning (ML) and deep learning (DL) methods, the role of AI will have significant impact on the imaging workflow and will eventually improve clinical decision making and outcomes.

METHODS AND RESULTS

 The first part of this narrative review discusses current research with an introduction to artificial intelligence in oncological hybrid imaging and key concepts in data science. The second part reviews relevant examples with a focus on applications in oncology as well as discussion of challenges and current limitations.

CONCLUSION

 AI applications have the potential to leverage the diagnostic data stream with high efficiency and depth to facilitate automated lesion detection, characterization, and therapy monitoring to ultimately improve quality and efficiency throughout the medical imaging workflow. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based therapy guidance in oncology. However, significant challenges remain regarding application development, benchmarking, and clinical implementation.

KEY POINTS

  · Hybrid imaging generates a large amount of multimodality medical imaging data with high complexity and depth.. · Advanced tools are required to enable fast and cost-efficient processing along the whole radiology value chain.. · AI applications promise to facilitate the assessment of oncological disease in hybrid imaging with high quality and efficiency for lesion detection, characterization, and response assessment. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based oncological therapy guidance.. · Selected applications in three oncological entities (lung, prostate, and neuroendocrine tumors) demonstrate how AI algorithms may impact imaging-based tasks in hybrid imaging and potentially guide clinical decision making..

Impact of [177Lu]Lu-PSMA-617 Radioligand Therapy on Reference Organ Uptake Assessed by [68Ga]Ga-PSMA-11-PET/CT

This study aims to assess the change in uptake to reference organs, including the liver, parotid and salivary glands after radioligand therapy (RLT) with [177Lu]Lu-PSMA-617 in relation to pretreatment imaging metrics. Eighty-five patients with mCRPC underwent [68Ga]Ga-PSMA-11 PET/CT imaging prior to (pre RLT PET) and after (post RLT PET) a median of 3 (IQR 2-6) RLT cycles with [177Lu]Lu-PSMA-617. PSMA-positive tumor burden was stratified into 4 groups based on modified PROMISE criteria (oligofocal, multifocal, disseminated, diffuse). Uptake (SUVmean, SUVmax) in liver tissue, parotid and submandibular glands was measured. A control group was established with 54 patients who had received two separate PET acquisitions following the same protocol (PET1, PET2) within 12 months for localized or oligofocal prostate cancer without RLT in the interim. Baseline uptake values (SUVmean, SUVmax) in parotid (10.8 ± 3.2, 16.8 ± 5.4) and submandibular glands (11.3 ± 2.8, 18.1 ± 4.7) are 2-fold compared to liver uptake (4.9 ± 1.4, 7.7 ± 2.0), with no significant change between PET 1 and PET 2 in the control group. In the RLT group, increasing tumor burden class is significantly associated with decreasing uptake in the liver (p = 0.013), parotid (p < 0.001) and submandibular glands (p < 0.001); this tumor sink effect by respective tumor burden is widely maintained after RLT (p = 0.011, p < 0.001, p < 0.001). RLT has a significant impact on salivary gland uptake with decreasing values per patient in all groups of disease burden change (up to -30.4% in submandibular glands, p < 0.001), while liver tissue shows rising values in patients with declining tumor burden throughout RLT (+18.6%, p = 0.020). Uptake in liver tissue and salivary glands on [68Ga]Ga-PSMA-11 PET/CT imaging is inversely related to tumor burden prior to and following RLT with [177Lu]Lu-PSMA-617. Per patient, salivary gland uptake is further reduced throughout RLT independently from tumor burden, while changes in liver uptake remain burden-dependent. Liver and salivary gland uptake-derived metrics and segmentation thresholds may thus be of limited value when used as reference for response assessment to RLT.

Response Evaluation Criteria in PSMA PET/CT (RECIP 1.0) in Metastatic Castration-resistant Prostate Cancer

Background Response Evaluation Criteria in Prostate-specific Membrane Antigen (PSMA) PET/CT (RECIP 1.0) initially integrated software-based quantitative assessment of PSMA-positive total tumor volume (TTV). Clinical implementation of such software is not expected soon, limiting the use of RECIP in practice. Purpose To assess the agreement of RECIP determined using tumor segmentation software (quantitative RECIP) with RECIP determined by qualitative reads by nuclear medicine physicians (visual RECIP) for response evaluation in metastatic castration-resistant prostate cancer. Materials and Methods This multicenter retrospective study at three academic centers included men who received lutetium 177 (177Lu) PSMA treatment between December 2014 and July 2019. PSMA PET/CT images at baseline and 12 weeks were assessed qualitatively by five readers for changes in TTV and for new lesions. Quantitative changes in TTV were also measured using tumor segmentation software. The status of new lesions was combined with qualitative changes in TTV to determine visual RECIP and with quantitative changes in TTV to determine quantitative RECIP. The primary outcomes were the agreement between visual and quantitative RECIP and the interreader reliability of visual RECIP according to the Fleiss κ. The secondary outcome was the association of visual RECIP with overall survival according to Cox regression. Results A total of 124 men (median age, 73 years [IQR, 67-76 years]) were included. Forty (32%) and 84 (68%) men had quantitative RECIP progressive disease (PD) and non-PD, respectively. Agreement between visual versus quantitative RECIP was excellent (κ = 0.89; 118 of 124 men [95%]). Agreement among readers in classifying visual RECIP PD versus non-PD was excellent (κ = 0.81; 103 of 124 men [83%]). RECIP PD was associated with significantly shorter overall survival compared with non-PD (hazard ratio, 2.6 [95% CI: 1.7, 3.8]; P < .001). Conclusion Qualitatively assessed RECIP demonstrated excellent agreement with quantitative RECIP and excellent interreader reliability and can be readily implemented in clinical practice for response evaluation in men with metastatic castration-resistant prostate cancer undergoing 177Lu-PSMA therapy. © RSNA, 2023 Supplemental material is available for this article.

PSMA PET Tumor-to-Salivary Gland Ratio to Predict Response to [177Lu]PSMA Radioligand Therapy: An International Multicenter Retrospective Study

Prostate-specific membrane antigen (PSMA)-targeted radioligand therapy can improve the outcome of patients with advanced metastatic castration-resistant prostate cancer, but patients do not respond uniformly. We hypothesized that using the salivary glands as a reference organ can enable selective patient stratification. We aimed to establish a PSMA PET tumor-to-salivary gland ratio (PSG score) to predict outcomes after [177Lu]PSMA. Methods: In total, 237 men with metastatic castration-resistant prostate cancer treated with [177Lu]PSMA were included. A quantitative PSG (qPSG) score (SUVmean ratio of whole-body tumor to parotid glands) was semiautomatically calculated on baseline [68Ga]PSMA-11 PET images. Patients were divided into 3 groups: high (qPSG > 1.5), intermediate (qPSG = 0.5-1.5), and low (qPSG < 0.5) scores. Ten readers interpreted the 3-dimensional maximum-intensity-projection baseline [68Ga]PSMA-11 PET images and classified patients into 3 groups based on visual PSG (vPSG) score: high (most of the lesions showed higher uptake than the parotid glands) intermediate (neither low nor high), and low (most of the lesions showed lower uptake than the parotid glands). Outcome data included a more than 50% prostate-specific antigen decline, prostate-specific antigen (PSA) progression-free survival, and overall survival (OS). Results: Of the 237 patients, the numbers in the high, intermediate, and low groups were 56 (23.6%), 163 (68.8%), and 18 (7.6%), respectively, for qPSG score and 106 (44.7%), 96 (40.5%), and 35 (14.8%), respectively, for vPSG score. The interreader reproducibility of the vPSG score was substantial (Fleiss weighted κ, 0.68). The more than 50% prostate-specific antigen decline was better in patients with a higher PSG score (high vs. intermediate vs. low, 69.6% vs. 38.7% vs. 16.7%, respectively, for qPSG [P < 0.001] and 63.2% vs 33.3% vs 16.1%, respectively, for vPSG [P < 0.001]). The median PSA progression-free survival of the high, intermediate, and low groups by qPSG score was 7.2, 4.0, and 1.9 mo (P < 0.001), respectively, by qPSG score and 6.7, 3.8, and 1.9 mo (P < 0.001), respectively, by vPSG score. The median OS of the high, intermediate, and low groups was 15.0, 11.2, and 13.9 mo (P = 0.017), respectively, by qPSG score and 14.3, 9.6, and 12.9 mo (P = 0.018), respectively, by vPSG score. Conclusion: The PSG score was prognostic for PSA response and OS after [177Lu]PSMA. The visual PSG score assessed on 3-dimensional maximum-intensity-projection PET images yielded substantial reproducibility and comparable prognostic value to the quantitative score.

Tumor Volume on PSMA PET as a Prognostic Biomarker in Prostate Cancer Patients Treated With Cabazitaxel

PURPOSE

The aim of this study was to evaluate the prognostic value of 68Ga-labeled prostate-specific membrane antigen (PSMA) PET/CT in metastatic castration-resistant prostate cancer patients receiving second-line chemotherapy with cabazitaxel.

METHODS

All patients with metastatic castration-resistant prostate cancer who underwent a PSMA PET/CT within 8 weeks before initiating the cabazitaxel treatment were retrospectively evaluated. The whole-body PSMA total tumor volume (PSMA-TV) was measured for each patient. Other factors such as prostate-specific antigen, hemoglobin, lactate dehydrogenase, and alkaline phosphatase were recorded. A log-rank cutoff finder was used to define the PSMA-TV optimal cutoff. Survival analyses were performed using Cox regression and Kaplan-Meier methods.

RESULTS

In total, 32 patients were included, receiving a median of 6 cycles of cabazitaxel (range, 2-10). After a median follow-up of 12 months, 28 patients presented disease progression, and 18 died. Baseline PSMA-TV presented a significant association with progression-free survival (PFS) and overall survival (OS; P = 0.035 and P = 0.002, respectively). Optimal PSMA-TV cutoffs were 515 mL for PFS and 473 mL for OS. Patients with low volume presented longer PFS and OS than those with high volume: median PFS, 21 versus 12 weeks, respectively (hazard ratio, 0.33; P = 0.017); and median OS, 24 versus 8.5 months, respectively (hazard ratio, 0.21; P = 0.002). On the multivariable analyses, PSMA-TV remained an independent predictor of OS (P = 0.016).

CONCLUSION

Our results show that total tumor volume measured on PSMA PET/CT is a prognostic biomarker in patients treated with cabazitaxel. High PSMA-TV before treatment initiation is associated with shorter PFS and OS.

Automated quantification of PET/CT skeletal tumor burden in prostate cancer using artificial intelligence: The PET index

PURPOSE

Consistent assessment of bone metastases is crucial for patient management and clinical trials in prostate cancer (PCa). We aimed to develop a fully automated convolutional neural network (CNN)-based model for calculating PET/CT skeletal tumor burden in patients with PCa.

METHODS

A total of 168 patients from three centers were divided into training, validation, and test groups. Manual annotations of skeletal lesions in [¹⁸F]fluoride PET/CT scans were used to train a CNN. The AI model was evaluated in 26 patients and compared to segmentations by physicians and to a SUV 15 threshold. PET index representing the percentage of skeletal volume taken up by lesions was estimated.

RESULTS

There was no case in which all readers agreed on prevalence of lesions that the AI model failed to detect. PET index by the AI model correlated moderately strong to physician PET index (mean r = 0.69). Threshold PET index correlated fairly with physician PET index (mean r = 0.49). The sensitivity for lesion detection was 65-76% for AI, 68-91% for physicians, and 44-51% for threshold depending on which physician was considered reference.

CONCLUSION

It was possible to develop an AI-based model for automated assessment of PET/CT skeletal tumor burden. The model's performance was superior to using a threshold and provides fully automated calculation of whole-body skeletal tumor burden. It could be further developed to apply to different radiotracers. Objective scan evaluation is a first step toward developing a PET/CT imaging biomarker for PCa skeletal metastases.

Outcomes and prognostic predictors of Lu-177 PSMA radioligand therapy in metastatic castration-resistant prostate cancer (Asian Population Study)

AIM

Lutetium-177 (Lu-177) prostate-specific membrane antigen radioligand therapy (PSMA-RLT) is a promising therapy for metastatic castration-resistant prostate cancer (mCRPC), but there is limited data of its efficacy and safety in Asian population. We aim to explore the clinical outcomes of Lu-177 PSMA-RLT in this population.

METHODS

We evaluated 84 patients with progressive mCRPC receiving Lu-177 PSMA-RLT between 9 May 2018 and 21 February 2022. Lu-177-PSMA-I&T was administered at 6-8-week intervals. Primary end point was overall survival (OS), and secondary end points included prostate-specific antigen (PSA) progression-free survival (PFS), PSA response rate, clinical response, toxicity assessment, and prognostic indicators.

RESULTS

The median OS and PSA PFS were 12.2 and 5.2 months, respectively. PSA decline of ≥50% was observed in 51.8% of patients. Patients achieving PSA response had longer median OS (15.0 vs. 9.5 months, p = .03) and PSA PFS (6.5 vs. 2.9 months, p < .001). Pain score improvement was seen in 19 out of 34 patients. A hematotoxicity of ≥grade 3 was observed in 13 out of 78 patients. Multivariable analyses showed that PSA velocity, alkaline phosphatase, hemoglobin (Hb), and the number of treatment cycles were independent prognostic indicators for OS. The retrospective design was the main limitation of the study.

CONCLUSIONS

Our study demonstrated a similar safety and efficacy of Lu-177 PSMA-RLT in Asian mCRPC patients compared to the existing literature. A PSA decline ≥50% was associated with longer OS and PSA PFS. Several prognostic indicators for patient outcomes were also identified.

Second Version of the Prostate Cancer Molecular Imaging Standardized Evaluation Framework Including Response Evaluation for Clinical Trials (PROMISE V2)

CONTEXT

Prostate-specific membrane antigen (PSMA) targeting positron emission tomography (PET) is emerging to become a reference imaging tool for the staging and restaging of patients with prostate cancer for both clinical routine and trials. The prostate cancer molecular imaging standardized evaluation (PROMISE) criteria have been proposed as a framework for whole-body staging (molecular imaging TNM staging, denoted miTNM staging) to describe the prostate cancer disease extent on PSMA-PET.

OBJECTIVE

To create a comprehensive and integrated framework for PSMA-PET image interpretation and reporting.

EVIDENCE ACQUISITION

We propose the PROMISE V2 framework, which integrates an updated miTNM system, improved assessment of local disease, and a slightly modified PSMA-expression score for clinical routine. We have added a response monitoring framework defining qualitative and quantitative parameters to be recorded for a longitudinal assessment in clinical trials.

EVIDENCE SYNTHESIS

We provide a comprehensive literature review on the current use of the PROMISE framework in clinical research and prospective trials. PROMISE variables demonstrate a clear association with survival. PSMA expression assessed by the PSMA-expression score was used in several trials, and a low PSMA-expression score is a negative prognosticator of overall survival after ¹⁷⁷Lu-PSMA radioligand therapy. The proposed imaging parameters recorded for response assessment in clinical trials can be utilized to determine response according to PSMA-PET progression (PPP) or Response Evaluation Criteria in PSMA-PET/Computed Tomography (RECIP) frameworks, but also future response criteria.

CONCLUSIONS

PROMISE V2 offers standardized reporting of disease extent for clinical routine and research. Parameters recorded within clinical trials facilitate objective response assessment.

PATIENT SUMMARY

Prostate-specific membrane antigen (PSMA) targeting positron emission tomography (PET) has become a standard imaging examination for prostate cancer. We propose a comprehensive framework for the analysis and reporting of PSMA-PET findings that will improve the communication between imaging experts and uro-oncologists.

Artificial Intelligence in Oncological Hybrid Imaging

BACKGROUND

Artificial intelligence (AI) applications have become increasingly relevant across a broad spectrum of settings in medical imaging. Due to the large amount of imaging data that is generated in oncological hybrid imaging, AI applications are desirable for lesion detection and characterization in primary staging, therapy monitoring, and recurrence detection. Given the rapid developments in machine learning (ML) and deep learning (DL) methods, the role of AI will have significant impact on the imaging workflow and will eventually improve clinical decision making and outcomes.

METHODS AND RESULTS

The first part of this narrative review discusses current research with an introduction to artificial intelligence in oncological hybrid imaging and key concepts in data science. The second part reviews relevant examples with a focus on applications in oncology as well as discussion of challenges and current limitations.

CONCLUSION

AI applications have the potential to leverage the diagnostic data stream with high efficiency and depth to facilitate automated lesion detection, characterization, and therapy monitoring to ultimately improve quality and efficiency throughout the medical imaging workflow. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based therapy guidance in oncology. However, significant challenges remain regarding application development, benchmarking, and clinical implementation.

KEY POINTS

· Hybrid imaging generates a large amount of multimodality medical imaging data with high complexity and depth.. · Advanced tools are required to enable fast and cost-efficient processing along the whole radiology value chain.. · AI applications promise to facilitate the assessment of oncological disease in hybrid imaging with high quality and efficiency for lesion detection, characterization, and response assessment. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based oncological therapy guidance.. · Selected applications in three oncological entities (lung, prostate, and neuroendocrine tumors) demonstrate how AI algorithms may impact imaging-based tasks in hybrid imaging and potentially guide clinical decision making..

CITATION FORMAT

· Feuerecker B, Heimer M, Geyer T et al. Artificial Intelligence in Oncological Hybrid Imaging. Fortschr Röntgenstr 2023; 195: 105 - 114.

Baseline [68Ga]Ga-PSMA-11 PET/CT before [177Lu]Lu-PSMA-617 Radioligand Therapy: Value of PSMA-Uptake Thresholds in Predicting Targetable Lesions

Baseline uptake on prostate-specific membrane antigen (PSMA)-targeted imaging is a prerequisite for radioligand therapy (RLT) with [177Lu]Lu-PSMA-617. This study aims to quantify lesion-based response to RLT in relation to pretreatment standard molecular imaging metrics derived from [68Ga]Ga-PSMA-11 PET/CT. Sixty-one patients with mCRPC underwent [68Ga]Ga-PSMA-11 PET/CT imaging before and after a median of 4 (IQR 2−6) RLT cycles. Maximum and mean standardized uptake values (SUVmax, SUVmean), as well as tumor-to-liver ratio (TLR), were assessed. A median of 12 (IQR 7−17) lesions was analyzed per patient, resulting in a total of 718 lesions. Lesions with ≥30% SUVmax decline or falling below the blood pool uptake were considered responsive; ≥30% SUVmax increase marked lesion progression. Additionally, 4-point visual scoring was performed according to E-PSMA consensus. In total, 550/718 (76.6%) lesions responded to RLT, including 389/507 (76.7%) bone metastases and 143/181 (79.0%) lymph node metastases. Baseline SUVmax, SUVmean, and TLR values were associated with lesion response by a moderate but significant correlation (rs = 0.33, p < 0.001, rs = 0.32, p < 0.001, and rs = 0.31, p < 0.001, respectively). For the classification of lesion progression based on baseline PSMA uptake, receiver operating characteristics (ROC) found SUVmax, SUVmean, and TLR to have comparable discriminatory value (AUC 0.85, 0.87, and 0.83). Of 42 tumor sites with baseline uptake below the liver (V-score < 2), 19/42 (45.2%) were responsive, 9/42 (21.4%) were stable, and 14/42 (33.3%) showed progression, leaving liver uptake a threshold with low prognostic value for the identification of RLT-refractory lesions (PPV 33%). This was observed accordingly for various liver uptake-based thresholds, including TLR < 1.5, <2.0 with a PPV at 24%, 20%, respectively. Standard uptake parameters quantified by routine baseline [68Ga]Ga-PSMA-11 PET/CT are moderately associated with post-treatment lesion response to [177Lu]Lu-PSMA-617. Commonly applied liver-based uptake thresholds have limited value in predicting refractory lesions at individual tumor sites.

Using 68Ga-PSMA-11 PET/CT for Therapy Response Assessment in Patients with Metastatic Castration-Resistant Prostate Cancer: Application of EAU/EANM Recommendations in Clinical Practice

For patients with metastatic castration-resistant prostate cancer (mCRPC), no reliable biomarkers for predicting therapeutic response or assisting in treatment selection and sequencing are currently available. Using the recent European Association of Urology and European Association of Nuclear Medicine recommendations, we aimed to compare response assessment between prostate-specific membrane antigen (PSMA) PET/CT and conventional imaging in mCRPC patients starting first-line treatment with a novel hormonal agent (NHA) and to perform a sequential comparative analysis of PSMA PET/CT-derived parameters after 4 and 12 wk of therapy. Methods: Data from 18 mCRPC patients who started NHA treatment and underwent ⁶⁸Ga-PSMA-11 PET/CT before therapy initiation (baseline), at week 4 (W4), and at week 12 (W12) in addition to conventional imaging (bone scintigraphy, CT) at baseline and W12 were retrospectively included. PET/CT images were quantitatively analyzed for maximum and mean SUV and total PSMA ligand-positive lesions. Comparative analysis of PET/CT-derived parameters was performed, and patients were classified as having nonprogressive disease or progressive disease (PD) according to ⁶⁸Ga-PSMA-11 PET/CT, prostate-specific antigen, and conventional imaging criteria. Results: Treatment response was evaluable by ⁶⁸Ga-PSMA-11 PET/CT in 16 of 18 patients (89%) and by conventional imaging in 11 of 18 patients (61%). Five of 16 patients classified as having PD by ⁶⁸Ga-PSMA-11 PET/CT at W12 had already met progression criteria at W4, and substantial agreement was observed between W4 and W12 (κ, 0.74) ⁶⁸Ga-PSMA-11 PET/CT results. Nonetheless, 2 of 16 patients (13%) were incorrectly classified as having PD because of a flare phenomenon on PSMA PET/CT that disappeared at W12. Conclusion: Volumetric assessments of ⁶⁸Ga-PSMA-11 PET/CT imaging can improve response evaluation in NHA-treated patients with mCRPC. Although early response assessments at W4 need to be approached with caution because of flare, ⁶⁸Ga-PSMA-11 PET/CT imaging at W4 and W12 revealed substantial agreement in therapy response assessments; these findings warrant further investigation to distinguish PD from flare at W4 and help improve the understanding of resistance to therapy.

Novel Framework for Treatment Response Evaluation Using PSMA PET/CT in Patients with Metastatic Castration-Resistant Prostate Cancer (RECIP 1.0): An International Multicenter Study

Our objective was to develop version 1.0 of a novel framework for response evaluation criteria in prostate-specific membrane antigen (PSMA) PET/CT (RECIP) and a composite response classification that combines responses by prostate-specific antigen (PSA) measurements and by RECIP 1.0 (PSA + RECIP). Methods: This was an international multicenter, retrospective study. One hundred twenty-four men with metastatic castration-specific prostate cancer (mCRPC) who underwent 177Lu-PSMA therapy and received PSMA PET/CT at baseline and at an interim time point of 12 wk were included. Pairs of baseline interim PET/CT scans were interpreted by consensus among 3 masked readers for appearance of new lesions. Tumor lesions were segmented, and total PSMA-positive tumor volume (PSMA-VOL) was obtained. Appearance of new lesions and changes in PSMA-VOL were combined to develop RECIP 1.0, which included classifications of complete response (RECIP-CR: absence of any PSMA-ligand uptake on interim PET/CT), partial response (RECIP-PR: decline ≥ 30% in PSMA-VOL and no appearance of new lesions), progressive disease (RECIP-PD: increase ≥ 20% in PSMA-VOL and appearance of new lesions), and stable disease (RECIP-SD: any condition but RECIP-PR or RECIP-PD). Changes in PSA levels at 12 wk by Prostate Cancer Working Group Criteria 3 were recorded. PSA + RECIP results were defined as response (PSA decline ≥ 50% or RECIP-PR/CR) or progression (PSA increase ≥ 25% or RECIP-PD). The study's primary outcome measure was the prognostic value of RECIP 1.0 for overall survival (OS). The secondary outcome measure was the prognostic accuracy (C-index) of PSA + RECIP versus PSA responses. Results: Patients with RECIP-PD (n = 39; 8.3 mo) had a shorter OS than patients with stable disease (RECIP-SD) (n = 47; 13.1 mo; P < 0.001) or RECIP-PR (n = 38; 21.7 mo; P < 0.001). In identifying responders and progressors, PSA + RECIP had C-indices superior to those of PSA only: 0.65 versus 0.62 (P = 0.028) and 0.66 versus 0.63 (P = 0.044), respectively. Conclusion: PSMA PET/CT by RECIP 1.0 is prognostic for OS and can be used as a response biomarker to monitor early efficacy of 177Lu-PSMA in men with mCRPC. PSA + RECIP may be used as a novel composite endpoint in mCRPC clinical trial design.

68Ga-PSMA-11 PET/CT Features Extracted from Different Radiomic Zones Predict Response to Androgen Deprivation Therapy in Patients with Advanced Prostate Cancer

Purpose: Prediction of treatment response to androgen deprivation therapy (ADT) prior to treatment initiation remains difficult. This study was undertaken to investigate whether 68Ga-PSMA-11 PET/CT features extracted from different radiomic zones within the prostate gland might predict response to ADT in patients with advanced prostate cancer (PCa). Methods: A total of 35 patients with prostate adenocarcinoma underwent two 68Ga-PSMA-11 PET/CT scans—termed PET-1 and PET-2—before and after 3 months of ADT, respectively. The prostate was divided into three radiomic zones, with zone-1 being the metabolic tumor zone, zone-2 the proximal peripheral tumor zone, and zone-3 the extended peripheral tumor zone. Patients in the response group were those who showed a reduction ratio > 30% for PET-derived parameters measured at PET-1 and PET-2. The remaining patients were classified as non-responders. Results: Seven features (glcm_idmn, glcm_idn, glcm_imc1, ngtdm_Contrast, glrlm_rln, gldm_dn, and shape_MeshVolume) from zone-1, two features (gldm_sdlgle and shape_MinorAxisLength) from zone-2, and two features (diagnostics_Mask-interpolated_Minimum and shape_Sphericity) from zone-3 successfully distinguished responders from non-responders to ADT. One predictive feature (shape_SurfaceVolumeRatio) was consistently identified in all of the three zones. Conclusions: this study demonstrates the potential usefulness of radiomic features extracted from different prostatic zones in distinguishing responders from non-responders prior to ADT initiation.

Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images

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 (TLV_auto) and total lesional uptake (TLU_auto) 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 TLV_auto and TLU_auto 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.

Measuring response in metastatic castration-resistant prostate cancer using PSMA PET/CT: comparison of RECIST 1.1, aPCWG3, aPERCIST, PPP, and RECIP 1.0 criteria

PURPOSE

To compare the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, the adapted Prostate Cancer Working Group Criteria 3 (aPCWG3), the adapted Positron Emission Tomography Response Criteria in Solid Tumors (aPERCIST), the PSMA PET Progression (PPP), and the Response Evaluation Criteria In PSMA-Imaging (RECIP) 1.0 for response evaluation using prostate-specific membrane antigen (PSMA)-PET/CT in men with metastatic castration-resistant prostate cancer (mCRPC) treated with ¹⁷⁷Lu-PSMA radioligand therapy.

METHODS

A total of 124 patients were included in this multicenter retrospective study. All patients received ¹⁷⁷Lu-PSMA and underwent PSMA-PET/CT scans at baseline (bPET) and at 12 weeks (iPET). Imaging responses according to RECIST 1.1, aPCWG3, aPERCIST, PPP, and RECIP 1.0 were interpreted by consensus among three blinded readers. Changes in total tumor burden were obtained using the semi-automatic qPSMA software. The response according to each criterion was classified to progressive disease (PD) vs no-PD. Primary outcome measure was the prognostic value (by Cox regression analysis) for overall survival (OS). Secondary outcome measure was the inter-reader reliability (by Cohen's κ coefficient).

RESULTS

A total of 43 (35%) of patients had non-measurable disease according to RECIST 1.1. Sixteen (13%), 66 (52%), 72 (58%), 69 (56%), and 39 (32%) of 124 patients had PD according to RECIST 1.1, aPCWG3, aPERCIST, PPP, and RECIP, respectively. PD vs no-PD had significantly higher risk of death according to aPCWG3 (HR = 2.37; 95%CI, 1.62-3.48; p < 0.001), aPERCIST (HR = 2.48; 95%CI, 1.68-3.66; p < 0.001), PPP (HR = 2.72; 95%CI, 1.85-4.01; p < 0.001), RECIP 1.0 (HR = 4.33; 95%CI, 2.80-6.70; p < 0.001), but not according to RECIST 1.1 (HR = 1.29; 95%CI, 0.73-2.27; p = 0.38). The κ index of RECIST 1.1, aPCWG3, aPERCIST 1.0, PPP, and RECIP 1.0 for identifying PD vs no-PD were 0.50 (95%CI, 0.32-0.76), 0.72 (95%CI, 0.63-0.82), 0.68 (95%CI, 0.63-0.73), 0.73 (95%CI, 0.63-0.83), and 0.83 (95%CI, 0.77-0.88), respectively.

CONCLUSION

PSMA-PET-specific criteria for early response evaluation in men with mCRPC treated with ¹⁷⁷Lu-PSMA achieved higher prognostic values and inter-reader reliabilities in comparison to conventional CT assessment or to criteria adapted to PSMA-PET from other imaging modalities. RECIP 1.0 identified the fewest patients with PD and achieved the highest risk of death for PD vs. no-PD, suggesting that other classification methods tend to overcall progression. Prospective validation of our findings on an independent patient cohort is warranted.

Freely available artificial intelligence for pelvic lymph node metastases in PSMA PET-CT that performs on par with nuclear medicine physicians

PURPOSE

The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [¹⁸F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers.

METHODS

[¹⁸F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement between the three readers were assessed in a separate test group of 50 patients.

RESULTS

The sensitivity of the AI method for detecting pelvic lymph node metastases was 82%, and the corresponding sensitivity for the human readers was 77% on average. The average number of false positives was 1.8 per patient. A total of 5-17 false negative lesions in the whole cohort were found, depending on which reader was used as a reference. The method is available for researchers at www.recomia.org .

CONCLUSION

This study shows that AI can obtain a sensitivity on par with that of physicians with a reasonable number of false positives. The difficulty in achieving high inter-observer sensitivity emphasizes the need for automated methods. On the road to qualifying AI tools for clinical use, independent validation is critical and allows performance to be assessed in studies from different hospitals. Therefore, we have made our AI tool freely available to other researchers.

Reduced Segmentation of Lesions Is Comparable to Whole-Body Segmentation for Response Assessment by PSMA PET/CT: Initial Experience with the Keyhole Approach

(1) Background: Prostate-specific membrane antigen (PSMA) positron emission tomography (PET)-derived parameters, such as the commonly used standardized uptake value (SUV) and PSMA-positive tumor volume (PSMA-TV), have been proposed for response assessment in metastatic prostate cancer (PCa) patients. However, the calculation of whole-body PSMA-TV remains a time-consuming procedure. We hypothesized that it may be possible to quantify changes in PSMA-TV by considering only a limited number of representative lesions. (2) Methods: Sixty-five patients classified into different disease stages were assessed by PSMA PET/CT for staging and restaging after therapy. Whole-body PSMA-TV and whole-body SUVmax were calculated. We then repeated this calculation only including the five or ten hottest or largest lesions. The corresponding serum levels of prostate-specific antigen (PSA) were also determined. The derived delta between baseline and follow-up values provided the following parameters: ΔSUVmaxall, ΔSUVmax10, ΔSUVmax5, ΔPSMA-TVall, ΔPSMA-TV10, ΔPSMA-TV5, ΔPSA. Finally, we compared the findings from our whole-body segmentation with the results from our keyhole approach (focusing on a limited number of lesions) and correlated all values with the biochemical response (ΔPSA). (3) Results: Among patients with metastatic hormone-sensitive PCa (mHSPC), none showed a relevant deviation for ΔSUVmax10/ΔSUVmax5 or ΔPSMA-TV10/ΔPSMA-TV5 compared to ΔSUVmaxall and ΔPSMA-TVall. For patients treated with taxanes, up to 6/21 (28.6%) showed clinically relevant deviations between ΔSUVmaxall and ΔSUVmax10 or ΔSUVmax5, but only up to 2/21 (9.5%) patients showed clinically relevant deviations between ΔPSMA-TVall and ΔPSMA-TV10 or ΔPSMA-TV5. For patients treated with radioligand therapy (RLT), up to 5/28 (17.9%) showed clinically relevant deviations between ΔSUVmaxall and ΔSUVmax10 or ΔSUVmax5, but only 1/28 (3.6%) patients showed clinically relevant deviations between ΔPSMA-TVall and ΔPSMA-TV10 or ΔPSMA-TV5. The highest correlations with ΔPSA were found for ΔPSMA-TVall (r ≥ 0.59, p ≤ 0.01), followed by ΔPSMA-TV10 (r ≥ 0.57, p ≤ 0.01) and ΔPSMA-TV5 (r ≥ 0.53, p ≤ 0.02) in all cohorts. ΔPSA only correlated with ΔSUVmaxall (r = 0.60, p = 0.02) and with ΔSUVmax10 (r = 0.53, p = 0.03) in the mHSPC cohort, as well as with ΔSUVmaxall (r = 0.51, p = 0.01) in the RLT cohort. (4) Conclusion: Response assessment using PSMA-TV with a reduced number of lesions is feasible, and may allow for a simplified evaluation process for PSMA PET/CT.

Application of SPECT and PET / CT with computer-aided diagnosis in bone metastasis of prostate cancer: a review

Bone metastasis has a significant influence on the prognosis of prostate cancer(PCa) patients. In this review, we discussed the current application of PCa bone metastasis diagnosis with single-photon emission computed tomography (SPECT) and positron emission tomography/computed tomography (PET/CT) computer-aided diagnosis(CAD) systems. A literature search identified articles concentrated on PCa bone metastasis and PET/CT or SPECT CAD systems using the PubMed database. We summarized the previous studies focused on CAD systems and manual quantitative markers calculation, and the coincidence rate was acceptable. We also analyzed the quantification methods, advantages, and disadvantages of CAD systems. CAD systems can detect abnormal lesions of PCa patients’ 99mTc-MDP-SPECT, 18F-FDG-PET/CT, 18F-NaF-PET/CT, and 68 Ga-PSMA PET/CT images automated or semi-automated. CAD systems can also calculate the quantitative markers, which can quantify PCa patients’ whole-body bone metastasis tumor burden accurately and quickly and give a standardized and objective result. SPECT and PET/CT CAD systems are potential tools to monitor and quantify bone metastasis lesions of PCa patients simply and accurately, the future clinical application of CAD systems in diagnosing PCa bone metastasis lesions is necessary and feasible.

Predictors and Real-World Use of Prostate-Specific Radioligand Therapy: PSMA and Beyond

PSMA is a transmembrane protein that is markedly overexpressed in prostate cancer, making it an excellent target for imaging and treating patients with prostate cancer. Several small molecule inhibitors and antibodies of PSMA have been radiolabeled for use as therapeutic agents and are currently under clinical investigation. PSMA-based radionuclide therapy is a promising therapeutic option for men with metastatic prostate cancer. The phase II TheraP study demonstrated superior efficacy, lower side effects, and improved patient-reported outcomes compared with cabazitaxel. The phase III VISION study demonstrated that radionuclide therapy with β-emitter ¹⁷⁷Lu-PSMA-617 can prolong survival and improve quality of life when offered in addition to standard-of-care therapy in men with PSMA-positive metastatic castration-resistant prostate cancer whose disease had progressed with conventional treatments. Nevertheless, up to 30% of patients have inherent resistance to PSMA-based radionuclide therapy, and acquired resistance is inevitable. Hence, strategies to increase the efficacy of PSMA-based radionuclide therapy have been under clinical investigation. These include better patient selection; increased radiation damage delivery via dosimetry-based administered dose or use of α-emitters instead of β-emitters; or using combinatorial approaches to overcome radioresistance mechanisms (innate or acquired), such as with novel hormonal agents, PARP inhibitors, or immunotherapy.

Prediction of early biochemical response after 177Lu-PSMA radioligand therapy with 68Ga-PSMA PET, a different perspective with quantitative parameters

OBJECTIVE

In this study, our aim was to evaluate the relationship of the quantitative data obtained from pretreatment 68Ga prostate-specific membrane antigen (PSMA) PET-computerized tomography (PET/CT) with treatment response of the patients with the diagnosis of metastatic castrationresistant prostate cancer (mCRPC) who received 177Lu-PSMA radioligand therapy (RLT).

METHODS

The patients who were given three or four cycles of 177Lu-PSMA RLT between January 2016 and June 2018 were evaluated retrospectively. Volumetric data; PSMA tumor volume (TV) and total lesion (TL) PSMA, were obtained from 68Ga-PSMA PET/CT for whole (PSMA-TVT and TL-PSMAT). The distance between the two furthest lesions (Dmax) was calculated. Posttreatment early prostate-specific antigen (PSA) values on the fourteenth day after treatment were obtained. According to the PSA responses, the patients were divided into two groups as progressed and nonprogressed. In univariate analysis, the relationship of PET quantitative data with biochemical response groups was evaluated with Mann-Whitney U test. Logistic regression was used in multivariate analysis.

RESULTS

A total of 38 patients were included in the study. In univariate analysis, Dmax, PSMA-TVT and TL-PSMAT values were obtained at lower levels in the progressed group. In multivariate analysis, only Dmax was found to be a prognostic factor in predicting early biochemical response.

CONCLUSION

Dmax is the most prognostic parameter in predicting the early biochemical response in patients with mCRPC; high total tumor volume and burden are also parameters that give us an idea about the response to treatment. The success rate will be higher if 177Lu-PSMA RLT treatment is planned for patients with higher tumor volume and spread.

Impact of Three-Month Androgen Deprivation Therapy on [68Ga]Ga-PSMA-11 PET/CT Indices in Men with Advanced Prostate Cancer-Results from a Pilot Prospective Study

Purpose: The purpose of this pilot prospective study is to examine the gallium-68-prostate-specific membrane antigen-11 ([68Ga]Ga-PSMA-11) positron emission tomography/computed tomography (PET/CT) imaging response in patients with advanced or metastatic hormone-naïve prostate cancer (PC) after 3 months of androgen deprivation therapy (ADT). Methods: We prospectively included men with untreated, clinical stage III or IV PC scheduled to receive ADT for at least 6 months. [68Ga]Ga-PSMA-11 PET/CT images were obtained before the start of ADT and 10−14 weeks thereafter. The following indices were examined: maximum standardized uptake value (SUVmax), mean SUV, PSMA total volume, and PSMA total lesion values of the prostate, nodes, bones, and whole-body. The therapeutic response was assessed using the modified PET response criteria in solid tumors 1.0. A subgroup analysis of patients with the International Society of Urological Pathology (ISUP) grade group 5 versus <5 was also performed. Results: A total of 30 patients were eligible. All PSMA PET/CT indices were significantly reduced (p < 0.001) after 3 months of ADT. Twenty-four (80%) patients showed partial response. Complete response, stable disease, and disease progression were observed in two patients each. Sixteen patients with ISUP grade group 5 showed a less prominent SUVmax reduction (p = 0.006), and none of them reached complete response. Conclusions: Three months of ADT in patients with untreated, advanced PC significantly reduced PSMA PET/CT indices. While most participants partially responded to ADT, patients with ISUP grade group 5 showed a less prominent SUVmax reduction. Collectively, our pilot results indicate that [68Ga]Ga-PSMA-11 PET/CT imaging holds promise to monitor treatment response after the first three months of ADT.

Semiautomatic assessment of whole-body tumor burden with 18F-PSMA-1007 in biochemical recurrent prostate cancer

OBJECTIVE

The aim of the study was to evaluate the 18F-PSMA-1007 PET/computed tomography (CT) semiautomatic volumetric parameters to assess the whole-body tumor burden and its correlation with prostate-specific antigen (PSA) and Gleason score in patients with biochemically recurrent prostate cancer (PCa).

MATERIALS AND METHODS

A total of 110 patients referred for 18F-PSMA-1007 PET/CT due to biochemical recurrence were retrospectively analyzed. Whole-body total lesion prostate-specific membrane antigen (wbTl-PSMA) and whole-body PSMA-derived tumor volume (wbPSMA-TV) metrics on 18F-PSMA-1007 were obtained semiautomatically in dedicated software. A Spearman test was performed to explore the correlation of volumetric imaging parameters with PSA levels and Gleason score. To analyze the association between volumetric measures and PSA subgroups, we used a Kruskal-Wallis test and a Dunn's test to identify each group causing an observed difference.

RESULTS

A total of 492 metastatic lesions were analyzed, and a significant correlation was found between wbTL-PSMA (R = 0.63, P < 0.0001) and wbPSMA-TV (R = 0.49, P < 0.0001) with serum PSA. A statistically significant difference with wbTL-PSMA was found in patients with a PSA less than or equal 0.5 ng/ml and PSA in the range of 0.51-1.0 ng/ml.

CONCLUSION

18F-PSMA-1007 PSMA volumetric parameters can provide a quantitative imaging biomarker for whole-body tumor burden.

Tumor Sink Effect in 68Ga-PSMA-11 PET: Myth or Reality?

We aimed to systematically determine the impact of tumor burden on ⁶⁸Ga-prostate-specific membrane antigen-11 (⁶⁸Ga-PSMA) PET biodistribution by the use of quantitative measurements. Methods: This international multicenter, retrospective analysis included 406 men with prostate cancer who underwent ⁶⁸Ga-PSMA PET/CT. Of these, 356 had positive findings and were stratified by quintiles into a very low (quintile 1, ≤25 cm³), low (quintile 2, 25-189 cm³), moderate (quintile 3, 189-532 cm³), high (quintile 4, 532-1,355 cm³), or very high (quintile 5, ≥1,355 cm³) total PSMA-positive tumor volume (PSMA-VOL). PSMA-VOL was obtained by semiautomatic segmentation of total tumor lesions using qPSMA software. Fifty prostate cancer patients with no PSMA-positive lesions (negative scan) served as a control group. Normal organs, which included salivary glands, liver, spleen, and kidneys, were semiautomatically segmented using ⁶⁸Ga-PSMA PET images, and SUV_mean was obtained. Correlations between the SUV_mean of normal organs and PSMA-VOL as continuous and categoric variables by quintiles were evaluated. Results: The median PSMA-VOL was 302 cm³ (interquartile range [IQR], 47-1,076 cm³). The median SUV_mean of salivary glands, kidneys, liver, and spleen was 10.0 (IQR, 7.7-11.8), 26.0 (IQR, 20.0-33.4), 3.7 (IQR, 3.0-4.7), and 5.3 (IQR, 4.0-7.2), respectively. PSMA-VOL showed a moderate negative correlation with the SUV_mean of the salivary glands (r = -0.44, P < 0.001), kidneys (r = -0.34, P < 0.001), and liver (r = -0.30, P < 0.001) and a weak negative correlation with the spleen SUV_mean (r = -0.16, P = 0.002). Patients with a very high PSMA-VOL (quintile 5, ≥1,355 cm³) had a significantly lower PSMA uptake in the salivary glands, kidneys, liver, and spleen than did the control group, with an average difference of -38.1%, -40.0%, -43.2%, and -34.9%, respectively (P < 0.001). Conclusion: Tumor sequestration affects ⁶⁸Ga-PSMA biodistribution in normal organs. Patients with a very high tumor load showed a significantly lower uptake of ⁶⁸Ga-PSMA in normal organs, confirming a tumor sink effect. As similar effects might occur with PSMA-targeted radioligand therapy, these patients might benefit from increased therapeutic activity without exceeding the radiation dose limit for organs at risk.

Implications of physics, chemistry and biology for dosimetry calculations using theranostic pairs

Theranostics is an emerging paradigm that combines imaging and therapy in order to personalize patient treatment. In nuclear medicine, this is achieved by using radiopharmaceuticals that target identical molecular targets for both imaging (using emitted gamma rays) and radiopharmaceutical therapy (using emitted beta, alpha or Auger-electron particles) for the treatment of various diseases, such as cancer. If the therapeutic radiopharmaceutical cannot be imaged quantitatively, a “theranostic pair” imaging surrogate can be used to predict the absorbed radiation doses from the therapeutic radiopharmaceutical. However, theranostic dosimetry assumes that the pharmacokinetics and biodistributions of both radiopharmaceuticals in the pair are identical or very similar, an assumption that still requires further validation for many theranostic pairs. In this review, we consider both same-element and different-element theranostic pairs and attempt to determine if factors exist which may cause inaccurate dose extrapolations in theranostic dosimetry, either intrinsic (e.g. chemical differences) or extrinsic (e.g. injecting different amounts of each radiopharmaceutical) to the radiopharmaceuticals. We discuss the basis behind theranostic dosimetry and present common theranostic pairs and their therapeutic applications in oncology. We investigate general factors that could create alterations in the behavior of the radiopharmaceuticals or the quantitative accuracy of imaging them. Finally, we attempt to determine if there is evidence showing some specific pairs as suitable for theranostic dosimetry. We show that there are a variety of intrinsic and extrinsic factors which can significantly alter the behavior among pairs of radiopharmaceuticals, even if they belong to the same chemical element. More research is needed to determine the impact of these factors on theranostic dosimetry estimates and on patient outcomes, and how to correctly account for them.

The added value of PSMA PET/MR radiomics for prostate cancer staging

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.

The prognostic power of 18F-FDG PET/CT extends to estimating systemic treatment response duration in metastatic castration-resistant prostate cancer (mCRPC) patients

BACKGROUND

We aimed to test whether the prognostic value of 18 F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG-PET/CT) in metastatic castration-resistant prostate cancer (mCRPC) extends to the estimation of systemic treatment response duration.

METHODS

mCRPC patients submitted to FDG-PET/CT in four Italian centers from 2005 to 2020 were retrospectively enrolled. Clinical and biochemical data at the time of imaging were collected, and SUV max of the hottest lesion, total metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were calculated. The correlation between PET- and biochemical-derived parameters with Overall Survival (OS) was analysed. The prediction of treatment response duration was assessed in the subgroup submitted to FDG-PET/CT in the six months preceding Chemotherapy (namely Docetaxel or Cabazitaxel, 24 patients) or Androgen-Receptor Targeted Agents (ARTA, namely Abiraterone or Enzalutamide, 20 patients) administration.

RESULTS

We enrolled 114 mCRPC patients followed-up for a median interval lasting 15 months. While at univariate analysis, prostate-specific antigen (PSA), Alkaline Phosphatase (ALP), MTV, and TLG were associated with OS, at the multivariate Cox regression analysis, the sole MTV could independently predict OS (p < 0.0001). In the subgroup submitted to FDG-PET/CT before the systemic treatment initiation, PSA and TLG could also predict treatment response duration independently (p < 0.05). Of note, while PSA could not indicate the best treatment choice, lower TLG was associated with higher success rates for ARTA but had no impact on chemotherapy efficacy.

CONCLUSIONS

FDG-PET/CT's prognostic value extends to predicting treatment response duration in mCRPC, thus potentially guiding the systemic treatment selection.