Comparison of Multiparametric Magnetic Resonance Imaging with Prostate-Specific Membrane Antigen Positron-Emission Tomography Imaging in Primary Prostate Cancer Diagnosis: A Systematic Review and Meta-Analysis

Comparing and Combining Artificial Intelligence and Spectral/Statistical Approaches for Elevating Prostate Cancer Assessment in a Biparametric MRI: A Pilot Study

Background: Prostate cancer management optimally requires non-invasive, objective, quantitative, accurate evaluation of prostate tumors. The current research applies visual inspection and quantitative approaches, such as artificial intelligence (AI) based on deep learning (DL), to evaluate MRI. Recently, a different spectral/statistical approach has been used to successfully evaluate spatially registered biparametric MRIs for prostate cancer. This study aimed to further assess and improve the spectral/statistical approach through benchmarking and combination with AI. Methods: A zonal-aware self-supervised mesh network (Z-SSMNet) was applied to the same 42-patient cohort from previous spectral/statistical studies. Using the probability of clinical significance of prostate cancer (PCsPCa) and a detection map, the affiliated tumor volume, eccentricity was computed for each patient. Linear and logistic regression were applied to the International Society of Urological Pathology (ISUP) grade and PCsPCa, respectively. The R, p-value, and area under the curve (AUROC) from the Z-SSMNet output were computed. The Z-SSMNet output was combined with the spectral/statistical output for multiple-variate regression. Results: The R (p-value)-AUROC [95% confidence interval] from the Z-SSMNet algorithm relating ISUP to PCsPCa is 0.298 (0.06), 0.50 [0.08-1.0]; relating it to the average blob volume, it is 0.51 (0.0005), 0.37 [0.0-0.91]; relating it to total tumor volume, it is 0.36 (0.02), 0.50 [0.0-1.0]. The R (p-value)-AUROC computations showed a much poorer correlation for eccentricity derived from the Z-SSMNet detection map. Overall, DL/AI showed poorer performance relative to the spectral/statistical approaches from previous studies. Multi-variable regression fitted AI average blob size and SCR results at a level of R = 0.70 (0.000003), significantly higher than the results for the univariate regression fits for AI and spectral/statistical approaches alone. Conclusions: The spectral/statistical approaches performed well relative to Z-SSMNet. Combining Z-SSMNet with spectral/statistical approaches significantly enhanced tumor grade prediction, possibly providing an alternative to current prostate tumor assessment.

Prediction of adverse pathology in prostate cancer using a multimodal deep learning approach based on [18F]PSMA-1007 PET/CT and multiparametric MRI

PURPOSE

Accurate prediction of adverse pathology (AP) in prostate cancer (PCa) patients is crucial for formulating effective treatment strategies. This study aims to develop and evaluate a multimodal deep learning model based on [18F]PSMA-1007 PET/CT and multiparametric MRI (mpMRI) to predict the presence of AP, and investigate whether the model that integrates [18F]PSMA-1007 PET/CT and mpMRI outperforms the individual PET/CT or mpMRI models in predicting AP.

METHODS

341 PCa patients who underwent radical prostatectomy (RP) with mpMRI and PET/CT scans were retrospectively analyzed. We generated deep learning signature from mpMRI and PET/CT with a multimodal deep learning model (MPC) based on convolutional neural networks and transformer, which was subsequently incorporated with clinical characteristics to construct an integrated model (MPCC). These models were compared with clinical models and single mpMRI or PET/CT models.

RESULTS

The MPCC model showed the best performance in predicting AP (AUC, 0.955 [95% CI: 0.932-0.975]), which is higher than MPC model (AUC, 0.930 [95% CI: 0.901-0.955]). The performance of the MPC model is better than that of single PET/CT (AUC, 0.813 [95% CI: 0.780-0.845]) or mpMRI (AUC, 0.865 [95% CI: 0.829-0.901]). Additionally, MPCC model is also effective in predicting single adverse pathological features.

CONCLUSION

The deep learning model that integrates mpMRI and [18F]PSMA-1007 PET/CT enhances the predictive capabilities for the presence of AP in PCa patients. This improvement aids physicians in making informed preoperative decisions, ultimately enhancing patient prognosis.

The Sensitivity and Specificity of Multiparametric Magnetic Resonance Imaging and Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography for Predicting Seminal Vesicle Invasion in Clinically Significant Prostate Cancer: A Multicenter Retrospective Study

Background/Objectives: The presence of seminal vesicle invasion (SVI) in prostate cancer (PCa) is associated with poorer postoperative outcomes. This study evaluates the predictive value of magnetic resonance imaging (MRI) and prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) for SVI in PCa. Methods: This cohort study included consecutive robotic prostatectomy patients for PCa at three Australian tertiary referral centres between April 2016 and September 2022. MRI and PSMA PET/CT results, clinicopathological variables, including age, BMI, prostate-specific antigen (PSA), PSA density, DRE, Biopsy Gleason score, Positive biopsy cores, PIRADS v2.1 score, MRI volume and MRI lesion size were extracted. The sensitivity, specificity, and accuracy of MRI and PSMA PET/CT for predicting SVI were compared with the histopathological results by receiver operating characteristic (ROC) analysis. Subgroup univariate and multivariate analysis was performed. Results: Of the 528 patients identified, 86 had SVI on final pathology. MRI had a low sensitivity of 0.162 (95% CI: 0.088-0.261) and a high specificity of 0.963 (95% CI: 0.940-0.979). The PSMA PET/CT had a low sensitivity of 0.439 (95% CI: 0.294-0591) and a high specificity of 0.933 (95% CI: 0.849-0.969). When MRI and PSMA PET/CT were used in combination, the sensitivity and specificity improved to 0.514 (95%CI: 0.356-0.670) and 0.880 (95% CI: 0.813-0.931). The multivariate regression showed a higher biopsy Gleason score (p = 0.033), higher PSA (p < 0.001), older age (p = 0.001), and right base lesions (p = 0.003) to be predictors of SVI. Conclusions: MRI and PSMA PET/CT independently underpredicted SVI. The sensitivity and AUC improved when they were used in combination. Multiple clinicopathological factors were associated with SVI on multivariate regression and predictive models incorporating this information may improve oncological outcomes.

Head-to-head comparison of prostate-specific membrane antigen positron emission tomography/computed tomography and multiparametric magnetic resonance imaging in the detection of biochemical recurrence of prostate cancer: a systematic review and meta-analysis

AIM

Our main goal of this meta-analytical analysis was to evaluate the diagnostic effectiveness of prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/computed tomography (CT) against multiparametric magnetic resonance imaging (mpMRI) in the context of identifying biochemical recurrence in patients with prostate cancer (PCa).

MATERIALS AND METHODS

A thorough search covering articles published until March 2023 was carried out across major databases such as PubMed, Embase, and Web of Science. Studies examining the direct comparison of PSMA PET/CT and mpMRI in patients with PCa suffering biochemical recurrence were included in the inclusion criteria. Using the renowned Quality Assessment of Diagnostic Performance Studies-2 technique, each study's methodological rigor was assessed.

RESULTS

We analyzed data from six eligible studies involving 290 patients in total. The combined data showed that for PSMA PET/CT and mpMRI, respectively, the pooled overall detection rates for recurrent PCa after definitive treatment were 0.69 (95% confidence interval [CI]: 0.45-0.89) and 0.70 (95% CI: 0.44-0.91). The detection rates for local recurrence were specifically 0.52 (95% CI: 0.39-0.65) and 0.62 (95% CI: 0.31-0.89), while they were 0.50 (95% CI: 0.26-0.74) and 0.32 (95% CI: 0.18-0.48) for lymph node metastasis. Notably, there was no discernible difference between the two imaging modalities in terms of the overall detection rate (P = 0.95). The detection rates for local recurrence and lymph node metastasis did not differ statistically significantly (P = 0.55, 0.23).

CONCLUSION

The performance of PSMA PET/CT and mpMRI in identifying biochemical recurrence in PCa appears to be comparable. However, the meta-analysis' findings came from research with modest sample sizes. In this context, more extensive research should be conducted in the future.

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.

Novel non-MRI imaging techniques for primary diagnosis of prostate cancer: micro-ultrasound, contrast-enhanced ultrasound, elastography, multiparametric ultrasound, and PSMA PET/CT

BACKGROUND

Multiparametric magnetic resonance imaging (mpMRI) provides enhanced diagnostic accuracy in the detection of prostate cancer, but is not devoid of limitations. Given the recent evolution of non-MRI imaging techniques, this critical review of the literature aimed at summarizing the available evidence on ultrasound-based and nuclear medicine imaging technologies in the initial diagnosis of PCa.

METHODS

Three databases (PubMed®, Web of Science™, and Scopus®) were queried for studies examining their diagnostic performance in the primary diagnosis of PCa, weighted against a histological confirmation of PCa diagnosis, using a free-text protocol. Retrospective and prospective studies, both comparative and non-comparative, systematic reviews (SR) and meta-analysis (MA) were included. Based on authors' expert opinion, studies were selected, data extracted, and results qualitatively described.

RESULTS

Micro-ultrasound (micro-US) appears as an appealing diagnostic strategy given its high accuracy in detection of PCa, apparently non-inferior to mpMRI. The use of multiparametric US (mpUS) likely gives an advantage in terms of effectiveness coming from the combination of different modalities, especially when certain modalities are combined. Prostate-specific membrane antigen (PSMA) PET/CT may represent a whole-body, one-step approach for appropriate diagnosis and staging of PCa. The direct relationship between lesions avidity of radiotracers and histopathologic and prognostic features, and its valid diagnostic performance represents appealing characteristics. However, intrinsic limits of each of these techniques exist and further research is needed before definitively considering them reliable tools for accurate PCa diagnosis. Other novel technologies, such as elastography and multiparametric US, currently relies on a limited number of studies, and therefore evidence about them remains preliminary.

CONCLUSION

Evidence on the role of non-MRI imaging options in the primary diagnosis of PCa is steadily building up. This testifies a growing interest towards novel technologies that might allow overcoming some of the limitations of current gold standard MRI imaging.

Multimodal radiomics based on 18F-Prostate-specific membrane antigen-1007 PET/CT and multiparametric MRI for prostate cancer extracapsular extension prediction

OBJECTIVES

To compare the performance of the multiparametric magnetic resonance imaging (mpMRI) radiomics and 18F-Prostate-specific membrane antigen (PSMA)-1007 PET/CT radiomics model in diagnosing extracapsular extension (EPE) in prostate cancer (PCa), and to evaluate the performance of a multimodal radiomics model combining mpMRI and PET/CT in predicting EPE.

METHODS

We included 197 patients with PCa who underwent preoperative mpMRI and PET/CT before surgery. mpMRI and PET/CT images were segmented to delineate the regions of interest and extract radiomics features. PET/CT, mpMRI, and multimodal radiomics models were constructed based on maximum correlation, minimum redundancy, and logistic regression analyses. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and indices derived from the confusion matrix.

RESULTS

AUC values for the mpMRI, PET/CT, and multimodal radiomics models were 0.85 (95% CI, 0.78-0.90), 0.73 (0.64-0.80), and 0.83 (0.75-0.89), respectively, in the training cohort and 0.74 (0.61-0.85), 0.62 (0.48-0.74), and 0.77 (0.64-0.87), respectively, in the testing cohort. The net reclassification improvement demonstrated that the mpMRI radiomics model outperformed the PET/CT one in predicting EPE, with better clinical benefits. The multimodal radiomics model performed better than the single PET/CT radiomics model (P < .05).

CONCLUSION

The mpMRI and 18F-PSMA-PET/CT combination enhanced the predictive power of EPE in patients with PCa. The multimodal radiomics model will become a reliable and robust tool to assist urologists and radiologists in making preoperative decisions.

ADVANCES IN KNOWLEDGE

This study presents the first application of multimodal radiomics based on PET/CT and MRI for predicting EPE.

68Ga-prostate specific membrane antigen-11 PET/CT versus multiparametric MRI in the detection of primary prostate cancer: A systematic review and head-to-head comparative meta-analysis

PURPOSE

The goal of this study was to evaluate the effectiveness of two diagnostic methods, 68Ga-PSMA-11 PET/CT and mpMRI, in detecting primary prostate cancer without limitations on the Gleason score.

METHODS

We conducted a comprehensive literature review, searching databases such as PubMed, Embase, and Web of Science until June 2023. Our objective was to identify studies that compared the efficacy of 68Ga-PSMA-11 PET/CT and mpMRI in detecting primary prostate cancer. To determine heterogeneity, the I2 statistic was used. Meta-regression analysis and leave-one-out sensitivity analysis were conducted to identify potential sources of heterogeneity.

RESULTS

Initially, 1286 publications were found, but after careful evaluation, only 16 studies involving 1227 patients were analyzed thoroughly. The results showed that the 68Ga-PSMA-11 PET/CT method had a pooled sensitivity and specificity of 0.87 (95 % CI: 0.80-0.92) and 0.80 (95 % CI: 0.69-0.89), respectively, for diagnosing prostatic cancer. Similarly, the values for mpMRI were determined as 0.84 (95 % CI: 0.75-0.92) and 0.74 (95 % CI: 0.61-0.86), respectively. There were no significant differences in diagnostic effectiveness observed when comparing two primary prostate cancer methodologies (pooled sensitivity P = 0.62, pooled specificity P = 0.50). Despite this, the funnel plots showed symmetry and the Egger test results (P values > 0.05) suggested there was no publication bias.

CONCLUSIONS

After an extensive meta-analysis, it was found that both 68Ga-PSMA-11 PET/CT and mpMRI demonstrate similar diagnostic effectiveness in detecting primary prostate cancer. Future larger prospective studies are warranted to investigate this issue further.

Deep Learning for Medical Image-Based Cancer Diagnosis

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Detecting localised prostate cancer using radiomic features in PSMA PET and multiparametric MRI for biologically targeted radiation therapy

BACKGROUND

Prostate-Specific Membrane Antigen (PSMA) PET/CT and multiparametric MRI (mpMRI) are well-established modalities for identifying intra-prostatic lesions (IPLs) in localised prostate cancer. This study aimed to investigate the use of PSMA PET/CT and mpMRI for biologically targeted radiation therapy treatment planning by: (1) analysing the relationship between imaging parameters at a voxel-wise level and (2) assessing the performance of radiomic-based machine learning models to predict tumour location and grade.

METHODS

PSMA PET/CT and mpMRI data from 19 prostate cancer patients were co-registered with whole-mount histopathology using an established registration framework. Apparent Diffusion Coefficient (ADC) maps were computed from DWI and semi-quantitative and quantitative parameters from DCE MRI. Voxel-wise correlation analysis was conducted between mpMRI parameters and PET Standardised Uptake Value (SUV) for all tumour voxels. Classification models were built using radiomic and clinical features to predict IPLs at a voxel level and then classified further into high-grade or low-grade voxels.

RESULTS

Perfusion parameters from DCE MRI were more highly correlated with PET SUV than ADC or T2w. IPLs were best detected with a Random Forest Classifier using radiomic features from PET and mpMRI rather than either modality alone (sensitivity, specificity and area under the curve of 0.842, 0.804 and 0.890, respectively). The tumour grading model had an overall accuracy ranging from 0.671 to 0.992.

CONCLUSIONS

Machine learning classifiers using radiomic features from PSMA PET and mpMRI show promise for predicting IPLs and differentiating between high-grade and low-grade disease, which could be used to inform biologically targeted radiation therapy planning.

Advances in Urological Cancer in 2022, from Basic Approaches to Clinical Management

This Special Issue includes 12 articles and 3 reviews dealing with several basic and clinical aspects of prostate, renal, and urinary tract cancer published during 2022 in Cancers, and intends to serve as a multidisciplinary chance to share the last advances in urological neoplasms [...].

Diagnostic Performance Evaluation of Multiparametric Magnetic Resonance Imaging in the Detection of Prostate Cancer with Supervised Machine Learning Methods

Prostate cancer is the second leading cause of cancer-related death in men. Its early and correct diagnosis is of particular importance to controlling and preventing the disease from spreading to other tissues. Artificial intelligence and machine learning have effectively detected and graded several cancers, in particular prostate cancer. The purpose of this review is to show the diagnostic performance (accuracy and area under the curve) of supervised machine learning algorithms in detecting prostate cancer using multiparametric MRI. A comparison was made between the performances of different supervised machine-learning methods. This review study was performed on the recent literature sourced from scientific citation websites such as Google Scholar, PubMed, Scopus, and Web of Science up to the end of January 2023. The findings of this review reveal that supervised machine learning techniques have good performance with high accuracy and area under the curve for prostate cancer diagnosis and prediction using multiparametric MR imaging. Among supervised machine learning methods, deep learning, random forest, and logistic regression algorithms appear to have the best performance.

The Role of [68Ga]PSMA PET/CT for Clinical Suspicion of Prostate Cancer in Patients with or without Previous Negative Biopsy: A Systematic Review

Simple Summary

In this paper we systematically evaluate the evidence regarding the role of [⁶⁸Ga]PSMA PET/CT for clinical suspicions of prostate cancer in patients with or without previous negative biopsy. A critical review of PubMed and Web of Science according to the PRISMA statement was conducted. Eighteen publications were selected for inclusion in the analysis. In 8 articles, there was a direct comparison with mpMRI. [⁶⁸Ga]PSMA PET/CT resulted more accurate in identifying primary prostate cancer with PSA values between 4 and 20 ng/mL than mpMRI. Moreover, its use combined with MRI improved sensitivity for csPCa detection, thus potentially avoiding unnecessary biopsies. Overall, [⁶⁸Ga]PSMA PET/CT resulted a promising technique in patients with clinical suspicion of PCa and precedent negative biopsy or contraindications to MRI.

Abstract

The purpose of the study is to systematically evaluate the evidence regarding the role of [⁶⁸Ga]PSMA PET/CT for clinical suspicions of prostate cancer in patients with or without previous negative biopsy. We performed a critical review of PubMed and Web of Science according to the PRISMA statement. Eighteen publications were selected for inclusion in this analysis. QUADAS-2 evaluation was adopted for quality analyses. [⁶⁸Ga]PSMA-11 was the radiotracer of choice in 15 studies, while [⁶⁸Ga]PSMA-617 was used in another 3. In 8 articles, there was a direct comparison with mpMRI. The total number of patients included was 1379, ranging from 15 to 291, with a median age of 64 years (range: 42–90). The median baseline PSA value was 12.9 ng/mL, ranging from 0.85 to 4156 ng/mL. Some studies evaluated the PSMA uptake comparing the SUVmax of suspicious lesions with the SUVmax of the normal biodistribution to find out optimal cut-off points. In addition, some studies suggested a significant association between PSA levels, PSA density, and [⁶⁸Ga]PSMA PET/CT finding. [⁶⁸Ga]PSMA PET/CT seems to be more accurate in identifying primary prostate cancer with PSA values between 4 and 20 ng/mL than mpMRI. Moreover, in some trials, the combination of PSMA PET/CT and MRI improved the NPV in the detection of clinically significant prostate cancer (csPCa) than MRI alone. Our findings are limited by the small numbers of studies and patient heterogeneity. [⁶⁸Ga]PSMA PET/CT is a promising technique in patients with clinical suspicion of PCa and precedent negative biopsy or contraindications to MRI. Furthermore, its use combined with MRI improves sensitivity for csPCa detection and can avoid unnecessary biopsies.

Bone Scintigraphy versus PSMA-Targeted PET/CT or PET/MRI in Prostate Cancer: Lessons Learned from Recent Systematic Reviews and Meta-Analyses

Positron emission tomography (PET) combined with computed tomography (PET/CT) or magnetic resonance imaging (PET/MRI) using several radiopharmaceuticals [...]