Search

Objective: To test the ability of high-performance machine learning (ML) models employing clinical, radiological, and radiomic variables to improve non-invasive prediction of the pathological status of prostate cancer (PCa) in a large, single-institution cohort., Methods: Patients who underwent multiparametric MRI and prostatectomy in our institution in 2015-2018 were considered; a total of 949 patients were included. Gradient-boosted decision tree models were separately trained using clinical features alone and in combination with radiological reporting and/or prostate radiomic features to predict pathological T, pathological N, ISUP score, and their change from preclinical assessment. Model behavior was analyzed in terms of performance, feature importance, Shapley additive explanation (SHAP) values, and mean absolute error (MAE). The best model was compared against a naïve model mimicking clinical workflow., Results: The model including all variables was the best performing (AUC values ranging from 0.73 to 0.96 for the six endpoints). Radiomic features brought a small yet measurable boost in performance, with the SHAP values indicating that their contribution can be critical to successful prediction of endpoints for individual patients. MAEs were lower for low-risk patients, suggesting that the models find them easier to classify. The best model outperformed (p ≤ 0.0001) clinical baseline, resulting in significantly fewer false negative predictions and overall was less prone to under-staging., Conclusions: Our results highlight the potential benefit of integrative ML models for pathological status prediction in PCa. Additional studies regarding clinical integration of such models can provide valuable information for personalizing therapy offering a tool to improve non-invasive prediction of pathological status., Clinical Relevance Statement: The best machine learning model was less prone to under-staging of the disease. The improved accuracy of our pathological prediction models could constitute an asset to the clinical workflow by providing clinicians with accurate pathological predictions prior to treatment., Key Points: • Currently, the most common strategies for pre-surgical stratification of prostate cancer (PCa) patients have shown to have suboptimal performances. • The addition of radiological features to the clinical features gave a considerable boost in model performance. Our best model outperforms the naïve model, avoiding under-staging and resulting in a critical advantage in the clinic. •Machine learning models incorporating clinical, radiological, and radiomics features significantly improved accuracy of pathological prediction in prostate cancer, possibly constituting an asset to the clinical workflow., (© 2024. The Author(s), under exclusive licence to European Society of Radiology.)

Aim: The present work reports updated oncological results and patients-reported outcomes at 5 years of phase II trial "Short-term high precision RT for early prostate cancer with SIB to the dominant intraprostatic lesion (DIL) for patients with early-stage PCa"., Methods: Data from patients enrolled within AIRC IG-13218 (NCT01913717) trial were analyzed. Clinical and GU/GI toxicity assessment and PSA measurements were performed every 3 months for at least 2 years after RT end. QoL of enrolled patients was assessed by IPSS, EORTC QLQ-C30, EORTC QLQ-PR25, and IIEF-5. Patients' score changes were calculated at the end of RT and at 1, 12, and 60 months after RT., Results: A total of 65 patients were included. At a median follow-up of 5 years, OS resulted 86%. Biochemical and clinical progression-free survival at 5 years were 95%. The median PSA at baseline was 6.07 ng/ml, while at last follow-up resulted 0.25 ng/ml. IPSS showed a statistically significant variation in urinary function from baseline (p = 0.002), with the most relevant deterioration 1 month after RT, with a recovery toward baseline at 12 months (p ≤ 0.0001). A numerical improvement in QoL according to the EORTC QLQ-C30 has been reported although not statistically significant. No change in sexual activity was recorded after RT., Conclusions: The study confirms that extreme hypofractionation with a DIL boost is safe and effective, with no severe effects on the QoL. The increasing dose to the DIL does not worsen the RT toxicity, thus opening the possibility of an even more escalated treatment., (© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: The primary aim of this study was to evaluate if exposure to 5-alpha-reductase inhibitors (5-ARIs) modifies the effect of MRI for the diagnosis of clinically significant Prostate Cancer (csPCa) (ISUP Gleason grade ≥ 2)., Methods: This study is a multicenter cohort study including patients undergoing prostate biopsy and MRI at 24 institutions between 2013 and 2022. Multivariable analysis predicting csPCa with an interaction term between 5-ARIs and PIRADS score was performed. Sensitivity, specificity, and negative (NPV) and positive (PPV) predictive values of MRI were compared in treated and untreated patients., Results: 705 patients (9%) were treated with 5-ARIs [median age 69 years, Interquartile range (IQR): 65, 73; median PSA 6.3 ng/ml, IQR 4.0, 9.0; median prostate volume 53 ml, IQR 40, 72] and 6913 were 5-ARIs naïve (age 66 years, IQR 60, 71; PSA 6.5 ng/ml, IQR 4.8, 9.0; prostate volume 50 ml, IQR 37, 65). MRI showed PIRADS 1-2, 3, 4, and 5 lesions in 141 (20%), 158 (22%), 258 (37%), and 148 (21%) patients treated with 5-ARIs, and 878 (13%), 1764 (25%), 2948 (43%), and 1323 (19%) of untreated patients (p < 0.0001). No difference was found in csPCa detection rates, but diagnosis of high-grade PCa (ISUP GG ≥ 3) was higher in treated patients (23% vs 19%, p = 0.013). We did not find any evidence of interaction between PIRADS score and 5-ARIs exposure in predicting csPCa. Sensitivity, specificity, PPV, and NPV of PIRADS ≥ 3 were 94%, 29%, 46%, and 88% in treated patients and 96%, 18%, 43%, and 88% in untreated patients, respectively., Conclusions: Exposure to 5-ARIs does not affect the association of PIRADS score with csPCa. Higher rates of high-grade PCa were detected in treated patients, but most were clearly visible on MRI as PIRADS 4 and 5 lesions., Trial Registration: The present study was registered at ClinicalTrials.gov number: NCT05078359., (© 2023. The Author(s).)

Purpose: To test any-cause discontinuation and ISUP GG upgrading rates during Active Surveillance (AS) in patients that underwent previous negative biopsies (PNBs) before prostate cancer (PCa) diagnosis vs. biopsy naive patients., Methods: Retrospective analysis of 961 AS patients (2008-2020). Three definitions of PNBs were used: (1) PNBs status (biopsy naïve vs. PNBs); (2) number of PNBs (0 vs. 1 vs. ≥ 2); (3) histology at last PNB (no vs. negative vs. HGPIN/ASAP). Kaplan-Meier plots and multivariable Cox models tested any-cause and ISUP GG upgrading discontinuation rates., Results: Overall, 760 (79.1%) vs. 201 (20.9%) patients were biopsy naïve vs. PNBs. Specifically, 760 (79.1%) vs. 138 (14.4%) vs. 63 (6.5%) patients had 0 vs. 1 vs. ≥ 2 PNBs. Last, 760 (79.1%) vs. 134 (13.9%) vs. 67 (7%) patients had no vs. negative PNB vs. HGPIN/ASAP. PNBs were not associated with any-cause discontinuation rates. Conversely, PNBs were associated with lower rates of ISUP GG upgrading: (1) PNBs vs. biopsy naïve (HR:0.6, p = 0.04); (2) 1 vs. 0 PNBs (HR:0.6, p = 0.1) and 2 vs. 0 PNBs, (HR:0.5, p = 0.1); (3) negative PNB vs. biopsy naïve (HR:0.7, p = 0.3) and HGPIN/ASAP vs. biopsy naïve (HR:0.4, p = 0.04). However, last PNB ≤ 18 months (HR:0.4, p = 0.02), but not last PNB > 18 months (HR:0.8, p = 0.5) were associated with lower rates of ISUP GG upgrading., Conclusion: PNBs status is associated with lower rates of ISUP GG upgrading during AS for PCa. The number of PNBs and time from last PNB to PCa diagnosis (≤ 18 months) appear also to be critical for patient selection., (© 2022. The Author(s).)

Purpose: To test discontinuation rates during Active Surveillance (AS) in patients diagnosed with incidental prostate cancers (IPCa) vs. tumors diagnosed at prostate biopsies (BxPCa)., Methods: Retrospective single center analysis of 961 vs. 121 BxPCa vs. IPCa patients (2008-2020). Kaplan-Meier plots and multivariable Cox regression models tested four different outcomes: (1) any-cause discontinuation; (2) discontinuation due to ISUP GG upgrading; (3) biopsy discontinuation due to ISUP GG upgrading or > 3 positive cores; (4) biopsy discontinuation or suspicious extraprostatic extension at surveillance mpMRI. Then, multivariable logistic regression models tested rates of clinically significant PCa (csPCa) (ISUP GG ≥ 3 or pT ≥ 3a or pN1) after radical prostatectomy (RP)., Results: Median time follow-up was 35 (19-64) months. IPCa patients were at lower risk of any-cause (3-year survival: 79.3 vs. 66%; HR: 0.5, p = 0.001) and biopsy/MRI AS discontinuation (3-year survival: 82.3 vs. 72.7%; HR: 0.5, p = 0.001), compared to BxPCa patients. Conversely, IPCa patients exhibited same rates of biopsy discontinuation and ISUP GG upgrading over time, relative to BxPCa. In multivariable logistic regression models, IPCa patients were associated with higher rates of csPCa at RP (OR: 1.4, p = 0.03), relative to their BxPCa counterparts., Conclusion: AS represents a safe management strategy for IPCa. Compared to BxPCa, IPCa patients are less prone to experience any-cause and biopsy/MRI AS discontinuation. However, the two mentioned groups present similar rates of biopsy discontinuation and ISUP GG upgrading over time. In consequence, tailored AS protocols with scheduled repeated surveillance biopsies should be offered to all newly diagnosed IPCa patients., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: To test the effect of perioperative chemotherapy (CHT) on overall mortality (OM) and cancer-specific mortality (CSM) in patients with locally advanced or metastatic squamous cell carcinoma of the urinary bladder (SCC UB)., Methods: Within the Surveillance, Epidemiology and End Results database (1988-2016), we identified 1,018 SCC UB patients (664 T 3-4a N 0 M 0 , 197 TanyN 1-3 M 0 and 156 T 4b N 0-3 or M 1 ), who underwent radical cystectomy with or without perioperative chemotherapy administration. Inverse probability of treatment-weighting (IPTW), Kaplan-Meier plots and Cox-regression models (CRMs) were used., Results: CHT was administrated in 116 (17.5%) T 3-4a N 0 M 0 , 77 (39.1%) TanyN 1-3 M 0 and 47 (30.1%) T 4b N 0-3 or M 1 patients. IPTW-adjusted 2-year cancer-specific survival (CSS) was 66.5 vs. 71.5% (p = 0.19), 60.9 vs. 29.5% (p < 0.001) and IPTW-adjusted 1-year CSS was 46.2 vs. 31.1% (p = 0.03) for CHT vs. no CHT administration in T 3-4a N 0 M 0 , TanyN 1-3 M 0 and T 4b N 0-3 or M 1 , respectively. In multivariable IPTW-adjusted CRMs, chemotherapy was an independent predictor of lower CSM in TanyN 1-3 M 0 (HR 0.44) and in T 4b N 0-3 or M 1 (HR 0.60), but not in T 3-4a N 0 M 0 (p = 0.6) patients. Virtually the same results were obtained on OM, as well as without IPTW-adjustment and after stratification according to age and gender., Conclusions: The use of perioperative CHT in patients with SCC UB confers survival benefit in the presence of T4b disease, lymph node or distant metastases. Conversely, patients with locally advanced disease but negative lymph node invasion do not benefit from its use. Pending higher quality data from prospective trials, these data should encourage the use of perioperative CHT in those high-risk patient groups.

Background: The United States Census Bureau recommends distinguishing between "Asians" vs. "Native Hawaiians or Other Pacific Islanders" (NHOPI). We tested for prognostic differences according to this stratification in patients with prostate cancer (PCa) of all stages., Methods: Descriptive statistics, time-trend analyses, Kaplan-Meier plots and multivariate Cox regression models were used to test for differences at diagnosis, as well as for cancer specific mortality (CSM) according to the Census Bureau's definition in either non-metastatic or metastatic patients vs. 1:4 propensity score (PS)-matched Caucasian controls, identified within the Surveillance, Epidemiology and End Results database (2004-2016)., Results: Of all 380,705 PCa patients, NHOPI accounted for 1877 (0.5%) vs. 23,343 (6.1%) remaining Asians vs. 93.4% Caucasians. NHOPI invariably harbored worse PCa characteristics at diagnosis. The rates of PSA ≥ 20 ng/ml, Gleason ≥ 8, T3/T4, N1- and M1 stages were highest for NHOPI, followed by Asians, followed by Caucasians (PSA ≥ 20: 18.4 vs. 14.8 vs. 10.2%, Gleason ≥ 8: 24.9 vs. 22.1, vs. 15.9%, T3/T4: 5.5 vs. 4.2 vs. 3.5%, N1: 4.4 vs. 2.8, vs. 2.7%, M1: 8.3 vs. 4.9 vs. 3.9%). Despite the worst PCa characteristics at diagnosis, NHOPI did not exhibit worse CSM than Caucasians. Moreover, despite worse PCa characteristics, Asians exhibited more favorable CSM than Caucasians in comparisons that focussed on non-metastatic and on metastatic patients., Conclusions: Our observations corroborate the validity of the distinction between NHOPI and Asian patients according to the Census Bureau's recommendation, since these two groups show differences in PSA, grade and stage characteristics at diagnosis in addition to exhibiting differences in CSM even after PS matching and multivariate adjustment.

Objectives: Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa)., Methods: This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis., Results: Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94., Conclusions: MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice., Key Points: • A radiomic model was used to classify PCa aggressiveness. • Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland. • The most predictive features belong to the texture (57%) and intensity (43%) domains.

Background: To compare survival outcomes of metastatic patients harbouring either papillary (pRCC) or clear-cell (ccRCC) renal cell carcinoma in overall population and according to treatment modality., Methods: Within the Surveillance, Epidemiology and End Results database (2006-2015), we identified 6800 patients (585 papillary and 6215 clear-cell) with metastatic RCC. Propensity-score (PS) matching, Kaplan-Meier plots and multivariable Cox-regression models (CRMs) were used., Results: Overall, 585 (8.6%) patients harboured pRCC. Rates of nodal metastases were higher in patients with pRCC (49.7 vs. 23.3%; p < 0.001). Median overall survival (OS) was 13 vs. 18 months for pRCC vs. ccRCC patients. After multivariable adjustments, no difference in OS was recorded. Furthermore, after propensity-score matching, virtually the same results were recorded. Median OS of pRCC vs. ccRCC was 8 vs. 4 months for no treatment (NT), 11 vs. 12 months for targeted therapy alone (TT), 17 vs. 35 months for cytoreductive nephrectomy alone (CN) and 18 vs. 25 months for combination of CN with TT., Conclusions: Metastatic pRCC patients exhibit poor survival, regardless of treatment received. Moreover, pRCC patients are more likely to present nodal metastases, compared to ccRCC patients, as demonstrated by twofold higher rates of lymph node invasion at diagnosis. These observations indicate that papillary variant represents more prognostically unfavorable tumor histology, in the context of metastatic RCC.

Purpose: To test the effect of tumor location (urachal vs. non-urachal) on cancer-specific mortality (CSM) in patients with adenocarcinoma of the urinary bladder (ADKUB)., Materials and Methods: Within the Surveillance, Epidemiology, and End Results registry (2004-2016), we identified patients with non-metastatic (≤ T4N0M0) ADKUB. Stratification was made according to tumor location: urachal vs. non-urachal ADKUB. Kaplan-Meier plots and multivariable Cox regression models were fitted before and after 1:3 propensity score (PS) matching and separate Cox regression models were refitted before and after inverse probability of treatment weighting (IPTW)., Results: Of 1681 patients, 226 (13.5%) vs. 1455 (86.5%) harboured urachal vs. non-urachal ADKUB, respectively. Five-year cancer-specific survival (CSS) rates were, respectively, 75 vs. 67% for urachal vs. non-urachal ADKUB (p = 0.001). In subgroup analyses of ≤ T2N0M0 patients, 5-year CSS rates were, respectively, 84 vs. 73% for urachal vs. non-urachal ADKUB (p = 0.006). In subgroup analyses of T3-4N0M0 patients, 5-year CSS rates were, respectively, 68 vs. 49% for urachal vs. non-urachal ADKUB (p < 0.001). In multivariable Cox regression models, urachal ADKUB was associated with lower CSM rates (HR 0.6; p = 0.01). Virtually, the same findings were recorded after 1:3 PS matching (HR 0.6; p = 0.009) as well as when Cox regression models were refitted after IPTW (HR 0.7; p = 0.01)., Conclusion: The distinction between urachal vs. non-urachal ADKUB indicates better prognosis when the origin of the tumor is urachal, regardless of methodological approach used for the comparison.

Objectives: To analyze the potential survival benefit of perioperative chemotherapy (CHT) in patients treated with nephroureterectomy (NU) for non-metastatic locally advanced upper tract urothelial carcinoma., Methods: Within the Surveillance, Epidemiology, and End Results database (2004-2014), we identified 1286 patients with T3 or T4, N 0-3 M0 UTUC. Kaplan-Meier plots, as well as multivariable Cox regression models (MCRMs) relying on inverse probability after treatment weighting (IPTW) and landmark analyses, were used to test the effect of CHT vs no CHT on overall mortality (OM) in the overall population (n =1286), as well as after stratification according to lymph node invasion (LNI)., Results: Overall, 37.4% patients received CHT. The CHT rate was higher with LNI (62.2% vs 35.2%, p < 0.001). In MCRMs, testing for OM in the overall population, CHT was associated with lower rates of OM (HR 0.71, CI 0.58-0.87; p = 0.001). Similarly, in MCRMs testing for OM in patients with LNI, CHT achieved independent predictor status for lower OM (HR 0.61, CI 0.48-0.78; p < 0.001). Conversely, in MCRMs testing for OM in patients without LNI, no CHT effect was recorded (HR 0.72, CI 0.52-1.01; p = 0.05). All results were confirmed after IPTW adjustment and in landmark analyses., Conclusions: Our results represent a contemporary North American report indicating lower OM after CHT for patients with locally advanced non-metastatic upper tract urothelial carcinoma, specifically in patients with T3-T4, N1-N3, M0 disease. Validation of the current and of the previous study is required within a randomized prospective design.

Purpose: To evaluate the oncological and functional outcomes of patients diagnosed with penile cancer undergoing conservative treatment through thulium-yttrium-aluminium-garnet (Tm:YAG) laser ablation., Methods: Twenty-six patients with a penile lesion underwent ablation with a RevoLix 200 W continuous-wave laser. The procedure was carried out with a pen-like laser hand piece, using a 360 μm laser fiber and 15-20 W of power. Median (IQR) follow-up time was 24 (15-30) months. Recurrence rate and post-operative sexual function were assessed., Results: Median age at surgery was 61 years. Median (inter quartile range) size of the lesions was 15 [10-20] mm. Overall, 11 (47.8%) and 12 (52.2%) at the final pathology presented in situ and invasive squamous cell carcinoma (SCC), respectively. The final pathological stage was pTis, pT1a, pT2, and pT3 in 11 (47.8%), 7 (30.4%), 3 (13.0%), and 2 (8.7%) patients, respectively. Moreover, four (17.4%) patients had a recurrence of which three (13.0%) and one (4.3%) patients developed an invasive or in situ recurrence, respectively. After treatment 6 (26.1%) patients reported a conserved penile sensitivity, while 13 (56.5%) and 4 (17.4%) patients experienced a better or worse sensitivity after ablation, respectively. Post-treatment sexual activity was achieved within the first month after laser ablation in 82.6% of the patients., Conclusion: Early stage penile carcinomas can be effectively treated with an organ preservation strategy. Tm:YAG conservative laser treatment is easy, safe and offers good functional outcome, with a minor impact on patient's quality of life.