Prostate cancer risk assessment and avoidance of prostate biopsies using fully automatic deep learning in prostate MRI: comparison to PI-RADS and integration with clinical data in nomograms.

OBJECTIVES: Risk calculators (RCs) improve patient selection for prostate biopsy with clinical/demographic information, recently with prostate MRI using the prostate imaging reporting and data system (PI-RADS). Fully-automated deep learning (DL) analyzes MRI data independently, and has been shown to be on par with clinical radiologists, but has yet to be incorporated into RCs. The goal of this study is to re-assess the diagnostic quality of RCs, the impact of replacing PI-RADS with DL predictions, and potential performance gains by adding DL besides PI-RADS. MATERIAL AND METHODS: One thousand six hundred twenty-seven consecutive examinations from 2014 to 2021 were included in this retrospective single-center study, including 517 exams withheld for RC testing. Board-certified radiologists assessed PI-RADS during clinical routine, then systematic and MRI/Ultrasound-fusion biopsies provided histopathological ground truth for significant prostate cancer (sPC). nnUNet-based DL ensembles were trained on biparametric MRI predicting the presence of sPC lesions (UNet-probability) and a PI-RADS-analogous five-point scale (UNet-Likert). Previously published RCs were validated as is; with PI-RADS substituted by UNet-Likert (UNet-Likert-substituted RC); and with both UNet-probability and PI-RADS (UNet-probability-extended RC). Together with a newly fitted RC using clinical data, PI-RADS and UNet-probability, existing RCs were compared by receiver-operating characteristics, calibration, and decision-curve analysis. RESULTS: Diagnostic performance remained stable for UNet-Likert-substituted RCs. DL contained complementary diagnostic information to PI-RADS. The newly-fitted RC spared 49% [252/517] of biopsies while maintaining the negative predictive value (94%), compared to PI-RADS ≥ 4 cut-off which spared 37% [190/517] (p < 0.001). CONCLUSIONS: Incorporating DL as an independent diagnostic marker for RCs can improve patient stratification before biopsy, as there is complementary information in DL features and clinical PI-RADS assessment. CLINICAL RELEVANCE STATEMENT: For patients with positive prostate screening results, a comprehensive diagnostic workup, including prostate MRI, DL analysis, and individual classification using nomograms can identify patients with minimal prostate cancer risk, as they benefit less from the more invasive biopsy procedure. KEY POINTS: The current MRI-based nomograms result in many negative prostate biopsies. The addition of DL to nomograms with clinical data and PI-RADS improves patient stratification before biopsy. Fully automatic DL can be substituted for PI-RADS without sacrificing the quality of nomogram predictions. Prostate nomograms show cancer detection ability comparable to previous validation studies while being suitable for the addition of DL analysis.

PD-L1 as a Urine Biomarker in Renal Cell Carcinoma-A Case Series and Proof-of-Concept Study.

BACKGROUND: Renal cell carcinoma (RCC) is among the most lethal urologic malignancies once metastatic. Current treatment approaches for metastatic RCC (mRCC) involve immune checkpoint inhibitors (ICIs) that target the PD-L1/PD-1 axis. High PD-L1 expression in tumor tissue has been identified as a negative prognostic factor in RCC. However, the role of PD-L1 as a liquid biomarker has not yet been fully explored. Herein, we analyze urine levels of PD-L1 in mRCC patients before and after either ICI therapy or surgical intervention, as well as in a series of patients with treatment-naïve RCC. PATIENTS AND METHODS: The mid-stream urine of patients with mRCC (n = 4) or treatment-naïve RCC, i.e., prior to surgery from two centers (cohort I, n = 49: cohort II, n = 29) was analyzed for PD-L1 by ELISA. The results from cohort I were compared to a control group consisting of patients treated for non-malignant urologic diseases (n = 31). In the mRCC group, urine PD-L1 levels were measured before and after tumor nephrectomy (n = 1) or before and after ICI therapy (n = 3). Exosomal PD-L1 in the urine was analyzed in selected patients by immunoblotting. RESULTS: A strong decrease in urine PD-L1 levels was found after tumor nephrectomy or following systemic treatment with ICIs. In patients with treatment-naïve RCC (cohort I), urine PD-L1 levels were significantly elevated in the RCC group in comparison to the control group (median 59 pg/mL vs. 25.7 pg/mL, p = 0.011). PD-L1 urine levels were found to be elevated, in particular, in low-grade RCCs in cohorts I and II. Exosomal PD-L1 was detected in the urine of a subset of patients. CONCLUSION: In this proof-of-concept study, we show that PD-L1 can be detected in the urine of RCC patients. Urine PD-L1 levels were found to correlate with the treatment response in mRCC patients and were significantly elevated in treatment-naïve RCC patients.

Weakly Supervised MRI Slice-Level Deep Learning Classification of Prostate Cancer Approximates Full Voxel- and Slice-Level Annotation: Effect of Increasing Training Set Size.

BACKGROUND: Weakly supervised learning promises reduced annotation effort while maintaining performance. PURPOSE: To compare weakly supervised training with full slice-wise annotated training of a deep convolutional classification network (CNN) for prostate cancer (PC). STUDY TYPE: Retrospective. SUBJECTS: One thousand four hundred eighty-nine consecutive institutional prostate MRI examinations from men with suspicion for PC (65 ± 8 years) between January 2015 and November 2020 were split into training (N = 794, enriched with 204 PROSTATEx examinations) and test set (N = 695). FIELD STRENGTH/SEQUENCE: 1.5 and 3T, T2-weighted turbo-spin-echo and diffusion-weighted echo-planar imaging. ASSESSMENT: Histopathological ground truth was provided by targeted and extended systematic biopsy. Reference training was performed using slice-level annotation (SLA) and compared to iterative training utilizing patient-level annotations (PLAs) with supervised feedback of CNN estimates into the next training iteration at three incremental training set sizes (N = 200, 500, 998). Model performance was assessed by comparing specificity at fixed sensitivity of 0.97 [254/262] emulating PI-RADS ≥ 3, and 0.88-0.90 [231-236/262] emulating PI-RADS ≥ 4 decisions. STATISTICAL TESTS: Receiver operating characteristic (ROC) and area under the curve (AUC) was compared using DeLong and Obuchowski test. Sensitivity and specificity were compared using McNemar test. Statistical significance threshold was P = 0.05. RESULTS: Test set (N = 695) ROC-AUC performance of SLA (trained with 200/500/998 exams) was 0.75/0.80/0.83, respectively. PLA achieved lower ROC-AUC of 0.64/0.72/0.78. Both increased performance significantly with increasing training set size. ROC-AUC for SLA at 500 exams was comparable to PLA at 998 exams (P = 0.28). ROC-AUC was significantly different between SLA and PLA at same training set sizes, however the ROC-AUC difference decreased significantly from 200 to 998 training exams. Emulating PI-RADS ≥ 3 decisions, difference between PLA specificity of 0.12 [51/433] and SLA specificity of 0.13 [55/433] became undetectable (P = 1.0) at 998 exams. Emulating PI-RADS ≥ 4 decisions, at 998 exams, SLA specificity of 0.51 [221/433] remained higher than PLA specificity at 0.39 [170/433]. However, PLA specificity at 998 exams became comparable to SLA specificity of 0.37 [159/433] at 200 exams (P = 0.70). DATA CONCLUSION: Weakly supervised training of a classification CNN using patient-level-only annotation had lower performance compared to training with slice-wise annotations, but improved significantly faster with additional training data. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Long-Term Survival of Patients with Stage T1N0M1 Renal Cell Carcinoma.

Metastatic renal cell carcinoma (RCC) is among the most lethal urological malignancies. However, small, localized RCCs (≤7 cm, stage T1) have an excellent prognosis. There is a rare patient subgroup diagnosed with synchronous distant metastasis (T1N0M1), of which very little is known in terms of survival outcomes and underlying disease biology. Herein, we examined the long-term survival of 27 patients with clear cell RCC (ccRCC) stage T1N0M1 in comparison to 18 patients without metastases (T1N0M0). Tumor tissue was stained by immunohistochemistry for CD8+ tumor infiltrating lymphocytes (TILs). As expected, patients with stage T1N0M1 showed a significantly worse median cancer specific survival (CSS; 2.8 years) than patients with stage T1N0M0 (17.7 years; HR 0.077; 95% CI, 0.022-0.262). However, eight patients (29.6%) with ccRCC stage T1N0M1 survived over five years, and three of those patients (11.1%) survived over a decade. Some of these patients benefitted from an intensified, multimodal treatment including metastasis-directed therapy. The number of CD8+ TILs was substantially higher in stage T1N0M1 ccRCCs than in stage T1N0M0 ccRCCs, suggesting a more aggressive tumor biology. In conclusion, long-term survival is possible in patients with ccRCC stage T1N0M1, with some patients benefitting from an intensified, multimodal treatment approach.

Digital Spatial Profiling Identifies the Tumor Periphery as a Highly Active Biological Niche in Clear Cell Renal Cell Carcinoma.

Clear cell renal cell carcinoma (ccRCC) is characterized by a high degree of intratumoral heterogeneity (ITH). Besides genomic ITH, there is considerable functional ITH, which encompasses spatial niches with distinct proliferative and signaling activities. The full extent of functional spatial heterogeneity in ccRCC is incompletely understood. In the present study, a total of 17 ccRCC tissue specimens from different sites (primary tumor, n = 11; local recurrence, n = 1; distant metastasis, n = 5) were analyzed using digital spatial profiling (DSP) of protein expression. A total of 128 regions of interest from the tumor periphery and tumor center were analyzed for the expression of 46 proteins, comprising three major signaling pathways as well as immune cell markers. Results were correlated to clinico-pathological variables. The differential expression of granzyme B was validated using conventional immunohistochemistry and was correlated to the cancer-specific patient survival. We found that a total of 37 proteins were differentially expressed between the tumor periphery and tumor center. Thirty-five of the proteins were upregulated in the tumor periphery compared to the center. These included proteins involved in cell proliferation, MAPK and PI3K/AKT signaling, apoptosis regulation, epithelial-to-mesenchymal transition, as well as immune cell markers. Among the most significantly upregulated proteins in the tumor periphery was granzyme B. Granzyme B upregulation in the tumor periphery correlated with a significantly reduced cancer-specific patient survival. In conclusion, this study highlights the unique cellular contexture of the tumor periphery in ccRCC. The correlation between granzyme B upregulation in the tumor periphery and patient survival suggests local selection pressure for aggressive tumor growth and disease progression. Our results underscore the potential of spatial biology for biomarker discovery in ccRCC and cancer in general.

Same-day repeatability and Between-Sequence reproducibility of Mean ADC in PI-RADS lesions.

PURPOSE: This study aimed to assess repeatability after repositioning (inter-scan), intra-rater, inter-rater and inter-sequence variability of mean apparent diffusion coefficient (ADC) measurements in MRI-detected prostate lesions. METHOD: Forty-three patients with suspicion for prostate cancer were included and received a clinical prostate bi-/multiparametric MRI examination with repeat scans of the T2-weighted and two DWI-weighted sequences (ssEPI and rsEPI). Two raters (R1 and R2) performed single-slice, 2D regions of interest (2D-ROIs) and 3D-segmentation-ROIs (3D-ROIs). Mean bias, corresponding limits of agreement (LoA), mean absolute difference, within-subject coefficient of variation (CoV) and repeatability/reproducibility coefficient (RC/RDC) were calculated. Bradley & Blackwood test was used for variance comparison. Linear mixed models (LMM) were used to account for multiple lesions per patient. RESULTS: Inter-scan repeatability, intra-rater and inter-sequence reproducibility analysis of ADC showed no significant bias. 3D-ROIs demonstrated significantly less variability than 2D-ROIs (p < 0.01). Inter-rater comparison demonstrated small significant systematic bias of 57 × 10-6 mm2/s for 3D-ROIs (p < 0.001). Intra-rater RC, with the lowest variation, was 145 and 189 × 10-6 mm2/s for 3D- and 2D-ROIs, respectively. For 3D-ROIs of ssEPI, RCs and RDCs were 190-198 × 10-6 mm2/s for inter-scan, inter-rater and inter-sequence variation. No significant differences were found for inter-scan, inter-rater and inter-sequence variability. CONCLUSIONS: In a single-scanner setting, single-slice ADC measurements showed considerable variation, which may be lowered using 3D-ROIs. For 3D-ROIs, we propose a cut-off of âˆ¼ 200 × 10-6 mm2/s for differences introduced by repositioning, rater or sequence effects. The results suggest that follow-up measurements should be possible by different raters or sequences.

Pseudoprospective Paraclinical Interaction of Radiology Residents With a Deep Learning System for Prostate Cancer Detection: Experience, Performance, and Identification of the Need for Intermittent Recalibration.

OBJECTIVES: The aim of this study was to estimate the prospective utility of a previously retrospectively validated convolutional neural network (CNN) for prostate cancer (PC) detection on prostate magnetic resonance imaging (MRI). MATERIALS AND METHODS: The biparametric (T2-weighted and diffusion-weighted) portion of clinical multiparametric prostate MRI from consecutive men included between November 2019 and September 2020 was fully automatically and individually analyzed by a CNN briefly after image acquisition (pseudoprospective design). Radiology residents performed 2 research Prostate Imaging Reporting and Data System (PI-RADS) assessments of the multiparametric dataset independent from clinical reporting (paraclinical design) before and after review of the CNN results and completed a survey. Presence of clinically significant PC was determined by the presence of an International Society of Urological Pathology grade 2 or higher PC on combined targeted and extended systematic transperineal MRI/transrectal ultrasound fusion biopsy. Sensitivities and specificities on a patient and prostate sextant basis were compared using the McNemar test and compared with the receiver operating characteristic (ROC) curve of CNN. Survey results were summarized as absolute counts and percentages. RESULTS: A total of 201 men were included. The CNN achieved an ROC area under the curve of 0.77 on a patient basis. Using PI-RADS ≥3-emulating probability threshold (c3), CNN had a patient-based sensitivity of 81.8% and specificity of 54.8%, not statistically different from the current clinical routine PI-RADS ≥4 assessment at 90.9% and 54.8%, respectively ( P = 0.30/ P = 1.0). In general, residents achieved similar sensitivity and specificity before and after CNN review. On a prostate sextant basis, clinical assessment possessed the highest ROC area under the curve of 0.82, higher than CNN (AUC = 0.76, P = 0.21) and significantly higher than resident performance before and after CNN review (AUC = 0.76 / 0.76, P ≤ 0.03). The resident survey indicated CNN to be helpful and clinically useful. CONCLUSIONS: Pseudoprospective paraclinical integration of fully automated CNN-based detection of suspicious lesions on prostate multiparametric MRI was demonstrated and showed good acceptance among residents, whereas no significant improvement in resident performance was found. General CNN performance was preserved despite an observed shift in CNN calibration, identifying the requirement for continuous quality control and recalibration.

Impact of Surgeon's Experience in Rigid versus Elastic MRI/TRUS-Fusion Biopsy to Detect Significant Prostate Cancer Using Targeted and Systematic Cores.

Multiparametric magnetic resonance imaging (mpMRI) and MRI/ultrasound fusion-targeted prostate biopsy (FB) have excellent sensitivity in detecting significant prostate cancer (sPC). FB platforms can be distinguished by rigid (RTB) or elastic image registration (ETB). We compared RTB and ETB by analyzing sPC detection rates of both RTB and ETB at different stages of the surgeons' learning curve. Patients undergoing RTB between 2015-2017 (n = 502) were compared to patients undergoing ETB from 2017-2019 (n = 437). SPC detection rates were compared by Chi-square-test on patient-basis. Combination of transperineal systematic biopsy and each TB served as reference and sub-analyses were performed for different grades of surgeon's experience. In the RTB subgroup, 233 men (46%) had sPC, compared to 201 (46%) in the ETB subgroup. RTB alone detected 94% of men with sPC and ETB 87% (p = 0.02). However, for at least intermediate-experienced surgeons (>100 FB), no differences occurred between RTB and ETB. In the total cohort, at least intermediate-experienced surgeons detected significantly more sPC (10%, p = 0.008) than novices. Thus, targeted transperineal MRI/TRUS-FB with a RTB registration system showed a similar sPC detection rate to ETB in experienced surgeons but a superior sPC detection rate to ETB in the total cohort. Low-experienced surgeons seem to benefit from RTB.

A Platform and Multisided Market for Translational, Software-Defined Medical Procedures in the Operating Room (OP 4.1): Proof-of-Concept Study.

BACKGROUND: Although digital and data-based technologies are widespread in various industries in the context of Industry 4.0, the use of smart connected devices in health care is still in its infancy. Innovative solutions for the medical environment are affected by difficult access to medical device data and high barriers to market entry because of proprietary systems. OBJECTIVE: In the proof-of-concept project OP 4.1, we show the business viability of connecting and augmenting medical devices and data through software add-ons by giving companies a technical and commercial platform for the development, implementation, distribution, and billing of innovative software solutions. METHODS: The creation of a central platform prototype requires the collaboration of several independent market contenders, including medical users, software developers, medical device manufacturers, and platform providers. A dedicated consortium of clinical and scientific partners as well as industry partners was set up. RESULTS: We demonstrate the successful development of the prototype of a user-centric, open, and extensible platform for the intelligent support of processes starting with the operating room. By connecting heterogeneous data sources and medical devices from different manufacturers and making them accessible for software developers and medical users, the cloud-based platform OP 4.1 enables the augmentation of medical devices and procedures through software-based solutions. The platform also allows for the demand-oriented billing of apps and medical devices, thus permitting software-based solutions to fast-track their economic development and become commercially successful. CONCLUSIONS: The technology and business platform OP 4.1 creates a multisided market for the successful development, implementation, distribution, and billing of new software solutions in the operating room and in the health care sector in general. Consequently, software-based medical innovation can be translated into clinical routine quickly, efficiently, and cost-effectively, optimizing the treatment of patients through smartly assisted procedures.

Mutations in TP53 or DNA damage repair genes define poor prognostic subgroups in primary prostate cancer.

BACKGROUND: Mutations in DNA damage repair genes, in particular genes involved in homology-directed repair, define a subgroup of men with prostate cancer with a more unfavorable prognosis but a therapeutic vulnerability to PARP inhibition. In current practice, mutational testing of prostate cancer patients is commonly done late i.e., when the tumor is castration resistant. In addition, most sequencing panels do not include TP53, one of the most crucial tumor suppressor genes in human cancer. In this proof-of-concept study, we sought to extend the clinical use of these molecular markers by exploring the early prognostic impact of mutations in TP53 and DNA damage repair genes in men with primary, nonmetastatic prostate cancer undergoing radical prostatectomy (RPX). METHODS: Tumor specimens from a cohort of 68 RPX patients with intermediate (n = 11, 16.2%) or high-risk (n = 57, 83.8%) disease were analyzed by targeted next generation sequencing using a 37 DNA damage repair and checkpoint gene panel including TP53. Sequencing results were correlated to clinicopathologic variables as well as PSA persistence or time to PSA failure. In addition, the distribution of TP53 and DNA damage repair gene mutations was analyzed in three large publicly available datasets (TCGA, MSKCC and SU2C). RESULTS: Of 68 primary prostate cancers analyzed, 23 (33.8%) were found to harbor a mutation in either TP53 (n = 12, 17.6%) or a DNA damage repair gene (n = 11, 16.2%). The vast majority of these mutations (22 of 23, 95.7%) were detected in primary tumors from patients with high-risk features. These mutations were mutually exclusive in our cohort and additional data mining suggests an enrichment of DNA damage repair gene mutations in TP53 wild-type tumors. Mutations in either TP53 or a DNA damage repair gene were associated with a significantly worse prognosis after RPX. Importantly, the presence of TP53/DNA damage repair gene mutations was an independent risk factor for PSA failure or PSA persistence in multivariate Cox regression models. CONCLUSION: TP53 or DNA damage repair gene mutations are frequently detected in primary prostate cancer with high-risk features and define a subgroup of patients with an increased risk for PSA failure or persistence after RPX. The significant adverse impact of these alterations on patient prognosis may be exploited to identify men with prostate cancer who may benefit from a more intensified treatment.

Imaging of Prostate Cancer.

BACKGROUND: Prostate cancer is the most common type of solid tumor in men and the second most common cause of cancer-related death in males in Germany. The conventional strategy for its primary detection, i.e., systematic ultrasound-guided prostate biopsy in men who have elevated PSA levels and/or positive findings on digital rectal examination, fails to reveal all cases. The same is true of the use of conventional computed tomography (CT), magnetic resonance imaging (MRI), and skeletal scintigraphy for the early detection of recurrences and distant metastases. METHODS: This review is based on pertinent publications retrieved by a selective search, including the German clinical practice guideline on prostate cancer and systematic review articles. RESULTS: Prospective multicenter trials have shown that the detection of clinically significant prostate cancer is markedly improved with multiparametric MRI (mpMRI) and MR/TRUS fusion biopsy (TRUS = transrectal ultrasonography), compared to conventional systematic biopsy. A recent Cochrane review showed that the rate of overdiagnosis of low-risk prostate cancer was reduced with mpMRI and MR/TRUS fusion biopsy compared with conventional systematic biopsy (95/1000 vs. 139/1000), and that clinically significant prostate cancer was more reliably detected (sensitivity 72% vs. 63%), albeit with slightly lower specificity (96% vs. 100%). Prostate- specific membrane antigen (PSMA) hybrid imaging improves the detection of lymphogenic and bony metastases in patients with high-risk prostate cancer. PSMA hybrid imaging is most commonly used to detect biochemical recurrences. A metaanalysis showed that the detection rate depends on the PSA concentration: 74.1% overall, 33.7% with PSA <0.2 ng/mL, and 91.7% with PSA ≥= 2.0 ng/mL. CONCLUSION: The appropriate use of mpMRI and MR/TRUS fusion biopsy improves the initial detection of prostate cancer as well as the assessment of the prognosis. PSMA hybrid imaging is useful for the staging of high-risk patients and for the detection of recurrences. These methods are now recommended in the German clinical practice guideline on prostate cancer as well as in guidelines from other countries.

Fully Automatic Deep Learning in Bi-institutional Prostate Magnetic Resonance Imaging: Effects of Cohort Size and Heterogeneity.

BACKGROUND: The potential of deep learning to support radiologist prostate magnetic resonance imaging (MRI) interpretation has been demonstrated. PURPOSE: The aim of this study was to evaluate the effects of increased and diversified training data (TD) on deep learning performance for detection and segmentation of clinically significant prostate cancer-suspicious lesions. MATERIALS AND METHODS: In this retrospective study, biparametric (T2-weighted and diffusion-weighted) prostate MRI acquired with multiple 1.5-T and 3.0-T MRI scanners in consecutive men was used for training and testing of prostate segmentation and lesion detection networks. Ground truth was the combination of targeted and extended systematic MRI-transrectal ultrasound fusion biopsies, with significant prostate cancer defined as International Society of Urological Pathology grade group greater than or equal to 2. U-Nets were internally validated on full, reduced, and PROSTATEx-enhanced training sets and subsequently externally validated on the institutional test set and the PROSTATEx test set. U-Net segmentation was calibrated to clinically desired levels in cross-validation, and test performance was subsequently compared using sensitivities, specificities, predictive values, and Dice coefficient. RESULTS: One thousand four hundred eighty-eight institutional examinations (median age, 64 years; interquartile range, 58-70 years) were temporally split into training (2014-2017, 806 examinations, supplemented by 204 PROSTATEx examinations) and test (2018-2020, 682 examinations) sets. In the test set, Prostate Imaging-Reporting and Data System (PI-RADS) cutoffs greater than or equal to 3 and greater than or equal to 4 on a per-patient basis had sensitivity of 97% (241/249) and 90% (223/249) at specificity of 19% (82/433) and 56% (242/433), respectively. The full U-Net had corresponding sensitivity of 97% (241/249) and 88% (219/249) with specificity of 20% (86/433) and 59% (254/433), not statistically different from PI-RADS (P > 0.3 for all comparisons). U-Net trained using a reduced set of 171 consecutive examinations achieved inferior performance (P < 0.001). PROSTATEx training enhancement did not improve performance. Dice coefficients were 0.90 for prostate and 0.42/0.53 for MRI lesion segmentation at PI-RADS category 3/4 equivalents. CONCLUSIONS: In a large institutional test set, U-Net confirms similar performance to clinical PI-RADS assessment and benefits from more TD, with neither institutional nor PROSTATEx performance improved by adding multiscanner or bi-institutional TD.

Comparison of single-scanner single-protocol quantitative ADC measurements to ADC ratios to detect clinically significant prostate cancer.

BACKGROUND: Mean ADC has high predictive value for the presence of clinically significant prostate cancer (sPC). Measurement variability is introduced by different scanners, protocols, intra-and inter-patient variation. Internal calibration by ADC ratios can address such fluctuations however can potentially lower the biological value of quantitative ADC determination by being sensitive to deviations in reference tissue signal. PURPOSE: To better understand the predictive value of quantitative ADC measurements in comparison to internal reference ratios when measured in a single scanner, single protocol setup. MATERIALS AND METHODS: 284 consecutive patients who underwent 3 T MRI on a single scanner followed by MRI-transrectal ultrasound fusion biopsy were included. A board-certified radiologist retrospectively reviewed all MRIs blinded to clinical information and placed regions of interest (ROI) on all focal lesions and the following reference regions: normal-appearing peripheral zone (PZNL) and transition zone (TZNL), the urinary bladder (BLA), and right and left internal obturator muscle (RIOM, LIOM). ROI-based mean ADC and ADC ratios to the reference regions were compared regarding their ability to predict the aggressiveness of prostate cancer. Spearman's rank correlation coefficient was used to estimate the correlation between ADC parameters, Gleason score (GS) and ADC ratios. The primary endpoint was presence of sPC, defined as a GS ≥ 3 + 4. Univariable and multivariable logistic regression models were constructed to predict sPC. Receiver operating characteristics curves (ROC) were used for visualization; DeLong test was used to evaluate the differences of the area under the curve (AUC). Bias-corrected AUC values and corresponding 95 %-CI were calculated using bootstrapping with 100 bootstrap samples. RESULTS: After exclusion of patients who received prior treatment, 259 patients were included in the final cohort of which 220 harbored 351 MR lesions. Mean ADC and ADC ratios demonstrated a negative correlation with the GS. Mean ADC had the strongest correlation with ρ of -0.34, followed by ADCratioPZNL (ρ=-0.32). All ADC parameters except ADCratioLIOM (p = 0.07) were associated with sPC p<0.05). Mean ADC and ADCratioPZNL had the highest ROC AUC of all parameters (0.68). Multivariable models with mean ADC improve predictive performance. CONCLUSIONS: A highly standardized single-scanner mean ADC measurement could not be improved upon using any of the single ADC ratio parameters or combinations of these parameters in predicting the aggressiveness of prostate cancer.

Standardized Magnetic Resonance Imaging Reporting Using the Prostate Cancer Radiological Estimation of Change in Sequential Evaluation Criteria and Magnetic Resonance Imaging/Transrectal Ultrasound Fusion with Transperineal Saturation Biopsy to Select Men on Active Surveillance.

BACKGROUND: Contemporary selection criteria for men with prostate cancer (PC) suitable for active surveillance (AS) are unsatisfactory, leading to high disqualification rates based on tumor misclassification. Conventional biopsy protocols are based on standard 12-core transrectal ultrasound (TRUS) biopsy. OBJECTIVE: To assess the value of magnetic resonance imaging (MRI)/TRUS fusion biopsy over 4-yr follow-up in men on AS for low-risk PC. DESIGN, SETTING, AND PARTICIPANTS: Between 2010 and 2018, a total of 273 men were included. Of them, 157 men with initial 12-core TRUS biopsy and 116 with initial MRI/TRUS fusion biopsy were followed by systematic and targeted transperineal MRI/TRUS fusion biopsies based on Prostate Cancer Research International Active Surveillance criteria. MRI from follow-up MRI/TRUS fusion biopsy was assessed using the Prostate Cancer Radiological Estimation of Change in Sequential Evaluation (PRECISE) scoring system. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: AS-disqualification rates for patients on AS initially diagnosed by either 12-core TRUS biopsy or by MRI/TRUS fusion biopsy were compared using Kaplan-Meier estimates, log-rank tests, and regression analyses. We also analyzed the influence of negative primary MRI and PRECISE scoring to predict AS disqualification using Kaplan-Meier estimates, log-rank tests, and receiver operating characteristic (ROC) curve analysis. RESULTS AND LIMITATIONS: Of men diagnosed by 12-core TRUS biopsy, 59% were disqualified from AS based on the results of subsequent MRI/TRUS fusion biopsy. In the initial MRI fusion biopsy cohort, upgrading occurred significantly less frequently (19%, p<0.001). ROC curve analyses demonstrated good discrimination for the PRECISE score with an area under the curve of 0.83. No men with a PRECISE score of 1 or 2 (demonstrating absence or downgrading of lesions in follow-up MRI) were disqualified from AS. In our cohort, a negative baseline MRI scan was not a predictor of nondisqualification from AS. Limitations include transperineal approach and extended systematic biopsies used with MRI/TRUS fusion biopsy, which may not be representative of other centers. CONCLUSIONS: MRI/TRUS fusion biopsies allow a reliable risk classification for patients who are candidates for AS. The application of the PRECISE scoring system demonstrated good discrimination. PATIENT SUMMARY: In this study, we investigated the value of multiparametric magnetic resonance imaging (MRI) and MRI/transrectal ultrasound (TRUS) fusion biopsies for the assessment of active surveillance (AS) reliability using the Prostate Cancer Radiological Estimation of Change in Sequential Evaluation criteria. Standard TRUS biopsies lead to significant underestimation of prostate cancer. In contrast, MRI/TRUS fusion biopsies allowed for a more reliable risk classification. For appropriate inclusion into AS, men should receive either an initial or a confirmatory MRI/TRUS fusion biopsy.

The Value of Prostate-specific Antigen Density for Prostate Imaging-Reporting and Data System 3 Lesions on Multiparametric Magnetic Resonance Imaging: A Strategy to Avoid Unnecessary Prostate Biopsies.

BACKGROUND: Multiparametric magnetic resonance imaging (mpMRI) has excellent sensitivity in detecting significant prostate cancer (sPC). Nevertheless, uncertainty exists regarding the management of Prostate Imaging-Reporting and Data System (PI-RADS) 3 lesions. OBJECTIVE: To investigate whether PI-RADS 3 lesions in combination with clinical parameters, especially prostate-specific antigen density (PSAD), can be used to exclude sPC. DESIGN, SETTING, AND PARTICIPANTS: A total of 455 consecutive biopsy-naïve men underwent MRI-guided transperineal prostate fusion biopsy at our department between 2017 and 2018. We identified 101 patients who had exclusively one or more PI-RADS 3 lesions on mpMRI. sPC was defined as intermediate- and high-risk PC (according to the D'Amico risk classification). OUTCOME MEASURES AND STATISTICAL ANALYSIS: Univariate logistic regression analysis was performed to test different clinical factors as predictors of sPC in men with PI-RADS 3 lesions. The probability of sPC prediction was calculated for different PSAD thresholds. RESULTS AND LIMITATIONS: Among patients with PI-RADS 3 lesions, PSAD was a significant predictor of sPC (p = 0.005). For a PI-RADS score of 3 the probability of excluding sPC was 85% (86/101), which increased to 98% (42/43) when combined with PSAD <0.1 ng/ml/ml. CONCLUSIONS: Inclusion of PSAD < 0.1 ng/ml/ml in the strategy for biopsy-naïve patients with equivocal mpMRI findings would allow a reduction in prostate biopsies in 43% (43/101) of cases at the cost of missing a very small number (2%, 1/43) of intermediate-risk PCs. PATIENT SUMMARY: At high-volume tertiary care centers with significant experience in prostate multiparametric magnetic resonance imaging, immediate biopsies could be safely omitted for men with lesions with a Prostate Imaging-Reporting and Data System score of 3 and prostate-specific antigen density of PSAD < 0.1 ng/ml/ml. Any decision to omit an immediate biopsy should be associated with close monitoring.

Measured Multipoint Ultra-High b-Value Diffusion MRI in the Assessment of MRI-Detected Prostate Lesions.

OBJECTIVES: The aim of this study was to assess quantitative ultra-high b-value (UHB) diffusion magnetic resonance imaging (MRI)-derived parameters in comparison to standard clinical apparent diffusion coefficient (SD-ADC-2b-1000, SD-ADC-2b-1500) for the prediction of clinically significant prostate cancer, defined as Gleason Grade Group greater than or equal to 2. MATERIALS AND METHODS: Seventy-three patients who underwent 3-T prostate MRI with diffusion-weighted imaging acquired at b = 50/500/1000/1500s/mm2 and b = 100/500/1000/1500/2250/3000/4000 s/mm2 were included. Magnetic resonance lesions were segmented manually on individual sequences, then matched to targeted transrectal ultrasonography/MRI fusion biopsies. Monoexponential 2-point and multipoint fits of standard diffusion and of UHB diffusion were calculated with incremental b-values. Furthermore, a kurtosis fit with parameters Dapp and Kapp with incremental b-values was obtained. Each parameter was examined for prediction of clinically significant prostate cancer using bootstrapped receiver operating characteristics and decision curve analysis. Parameter models were compared using Vuong test. RESULTS: Fifty of 73 men (age, 66 years [interquartile range, 61-72]; prostate-specific antigen, 6.6 ng/mL [interquartile range, 5-9.7]) had 64 MRI-detected lesions. The performance of SD-ADC-2b-1000 (area under the curve, 0.82) and SD-ADC-2b-1500 (area under the curve, 0.82) was not statistically different (P = 0.99), with SD-ADC-2b-1500 selected as reference. Compared with the reference model, none of the 19 tested logistic regression parameter models including multipoint and 2-point UHB-ADC, Dapp, and Kapp with incremental b-values of up to 4000 s/mm2 outperformed SD-ADC-2b-1500 (all P's > 0.05). Decision curve analysis confirmed these results indicating no higher net benefit for UHB parameters in comparison to SD-ADC-2b-1500 in the clinically important range from 3% to 20% of cancer threshold probability. Net reduction analysis showed no reduction of MR lesions requiring biopsy. CONCLUSIONS: Despite evaluation of a large b-value range and inclusion of 2-point, multipoint, and kurtosis models, none of the parameters provided better predictive performance than standard 2-point ADC measurements using b-values 50/1000 or 50/1500. Our results suggest that most of the diagnostic benefits available in diffusion MRI are already represented in an ADC composed of one low and one 1000 to 1500 s/mm2 b-value.

Comparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System.

PURPOSE: A recently developed deep learning model (U-Net) approximated the clinical performance of radiologists in the prediction of clinically significant prostate cancer (sPC) from prostate MRI. Here, we compare the agreement between lesion segmentations by U-Net with manual lesion segmentations performed by different radiologists. MATERIALS AND METHODS: 165 patients with suspicion for sPC underwent targeted and systematic fusion biopsy following 3 Tesla multiparametric MRI (mpMRI). Five sets of segmentations were generated retrospectively: segmentations of clinical lesions, independent segmentations by three radiologists, and fully automated bi-parametric U-Net segmentations. Per-lesion agreement was calculated for each rater by averaging Dice coefficients with all overlapping lesions from other raters. Agreement was compared using descriptive statistics and linear mixed models. RESULTS: The mean Dice coefficient for manual segmentations showed only moderate agreement at 0.48-0.52, reflecting the difficult visual task of determining the outline of otherwise jointly detected lesions. U-net segmentations were significantly smaller than manual segmentations (p < 0.0001) and exhibited a lower mean Dice coefficient of 0.22, which was significantly lower compared to manual segmentations (all p < 0.0001). These differences remained after correction for lesion size and were unaffected between sPC and non-sPC lesions and between peripheral and transition zone lesions. CONCLUSION: Knowledge of the order of agreement of manual segmentations of different radiologists is important to set the expectation value for artificial intelligence (AI) systems in the task of prostate MRI lesion segmentation. Perfect agreement (Dice coefficient of one) should not be expected for AI. Lower Dice coefficients of U-Net compared to manual segmentations are only partially explained by smaller segmentation sizes and may result from a focus on the lesion core and a small relative lesion center shift. Although it is primarily important that AI detects sPC correctly, the Dice coefficient for overlapping lesions from multiple raters can be used as a secondary measure for segmentation quality in future studies. KEY POINTS: · Intermediate human Dice coefficients reflect the difficulty of outlining jointly detected lesions.. · Lower Dice coefficients of deep learning motivate further research to approximate human perception.. · Comparable predictive performance of deep learning appears independent of Dice agreement.. · Dice agreement independent of significant cancer presence indicates indistinguishability of some benign imaging findings.. · Improving DWI to T2 registration may improve the observed U-Net Dice coefficients.. CITATION FORMAT: · Schelb P, Tavakoli AA, Tubtawee T et al. Comparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System. Fortschr Röntgenstr 2021; 193: 559 - 573.

Diagnostic Accuracy of 18F-PSMA-1007 PET/CT Imaging for Lymph Node Staging of Prostate Carcinoma in Primary and Biochemical Recurrence.

Prostate-specific membrane antigen (PSMA)-ligand PET/CT is performed on patients with prostate cancer to stage the disease initially or to identify sites of recurrence after definitive therapy. On the basis of clinical results, 18F-PSMA-1007 is a promising PSMA PET tracer, but detailed histologic confirmation has been lacking. Methods: Ninety-six patients with prostate cancer underwent 18F-PSMA-1007 PET/CT followed by either radical prostatectomy with lymphadenectomy or salvage lymphadenectomy. The histologic findings of PSMA PET-positive nodes were analyzed retrospectively. A lesion-based and patient-based analysis was performed comparing all positive lesions and only lesions larger than 3 mm on histopathology. Results: Of the patients, 90.6% received 18F-PSMA-1007 PET/CT for staging before the primary treatment, whereas 9.4% underwent imaging for biochemical recurrence. In 34.4% of the cohort, positive lymph nodes were present on imaging. In total, 1,746 lymph nodes were dissected in 96 patients. 18F-PSMA-1007 PET had a lesion-based sensitivity of 81.7%, a specificity of 99.6%, a positive predictive value of 92.4%, and a negative predictive value of 98.9% for detecting positive lymph nodes larger than 3 mm. In the analysis of all malignant nodes regardless of size, the overall sensitivity, specificity, positive predictive value, and negative predictive value on lesion-based analysis were 71.2%, 99.5%, 91.3%, and 97.9%, respectively. The patient-based analysis showed a sensitivity of 85.9% and a specificity of 99.5% for lymph nodes larger than 3 mm. Conclusion:18F-PSMA-1007 PET/CT reliably detects malignant lymph nodes and has an exceptional specificity of more than 99% for nodal metastases.

High prevalence of DNA damage repair gene defects and TP53 alterations in men with treatment-naïve metastatic prostate cancer -Results from a prospective pilot study using a 37 gene panel.

BACKGROUND: Defects in DNA damage repair genes characterize a subset of men with prostate cancer and provide an attractive opportunity for precision oncology approaches. The prevalence of such perturbations in newly diagnosed, treatment-naïve patients with a high risk for lethal disease outcome, however, has not been sufficiently explored. PATIENTS AND METHODS: Prostate cancer specimens from 67 men with newly diagnosed early onset, localized high-risk/locally advanced or metastatic prostate cancer were included in this prospective pilot study. Tumor samples, including 30 prostate biopsies, were analyzed by targeted next generation sequencing using a formalin-fixed, paraffin-embedded tissue-optimized 37 DNA damage repair and checkpoint gene panel. RESULTS: The drop-out rate due to an insufficient quantity of DNA was 4.5% (3 of 67 patients). In the remaining 64 patients, the rate of pathogenic DNA damage repair gene mutations was 26.6%. The highest rate of pathogenic DNA damage repair and checkpoint gene mutations was found in men with treatment-naïve metastatic prostate cancer (38.9%). In addition, a high number of likely pathogenic mutations and gene deletions were detected. Altogether, one or more pathogenic mutation, likely pathogenic mutation or gene deletion affected 43 of 64 patients (67.2%) including 29 of 36 patients (80.6%) with treatment-naïve metastatic prostate cancer. Men with metastatic prostate cancer showed a high prevalence of alterations in TP53 (36.1%). CONCLUSIONS: This pilot study demonstrates the feasibility, performance and clinical relevance of somatic targeted next generation sequencing using a unique 37 DNA damage repair and checkpoint gene panel under routine conditions. Our results indicate that this approach can detect actionable DNA repair gene alterations, uncommon mutations as well as mutations associated with therapy resistance in a high number of patients, in particular patients with treatment-naïve metastatic prostate cancer.

Microenvironment-Derived FGF-2 Stimulates Renal Cell Carcinoma Cell Proliferation through Modulation of p27Kip1: Implications for Spatial Niche Formation and Functional Intratumoral Heterogeneity.

BACKGROUND/OBJECTIVE: Clear cell renal cell carcinoma (ccRCC) is characterized by a high degree of functional intratumoral heterogeneity (ITH). This is highlighted by the finding that tumor cell proliferation and intracellular signaling occur preferentially in the tumor periphery. The driving forces for such a spatial organization are largely unknown. Herein, we investigate the role of the tumor microenvironment in the control of tumor cell proliferation and functional ITH. METHODS: Conditioned media (CM) derived from nonmalignant peritumoral kidney tissue were used to stimulate RCC cells in vitro. A neutralization assay was used to characterize the role of FGF-2 in the CM. The molecular mechanisms underlying the action of CM on RCC cells were investigated using immunoblotting, flow cytometry and immunofluorescence microscopy. Lastly, a series of ccRCCs were stained for Ki-67 and p27Kip1, and expression was analyzed in both tumor periphery and center. RESULTS: We show that CM derived from nonmalignant kidney cells adjacent to an RCC can downregulate the expression of the CDK inhibitor p27Kip1 through enhanced protein degradation in an FGF-2-dependent fashion. FGF-2 functions mainly through the PI3K/AKT pathway downstream of its receptors, and RCC cells with constitutively high AKT activity show not only an enhanced degradation of p27Kip1 through the Emi1-Skp2 axis, but also a subcellular mislocalization of p27Kip1 to the cytoplasmic compartment. Such a mislocalization was also detected in the tumor periphery in vivo suggesting that p27Kip1 plays an important role in shaping this spatial niche. CONCLUSIONS: Our results suggest that the tumor microenvironment is involved in shaping the tumor peripheral niche by stimulating the enhanced proliferation that is characteristic for this zone.