Demographic and Clinical Characteristics of Malignant Solitary Fibrous Tumors: A SEER Database Analysis.

BACKGROUND/OBJECTIVES: Solitary fibrous tumors (SFTs) represent a rare mesenchymal malignancy that can occur anywhere in the body. Due to the low prevalence of the disease, there is a lack of contemporary data regarding patient demographics and cancer-control outcomes. METHODS: Within the SEER database (2000-2019), we identified 1134 patients diagnosed with malignant SFTs. The distributions of patient demographics and tumor characteristics were tabulated. Cumulative incidence plots and competing risks analyses were used to estimate cancer-specific mortality (CSM) after adjustment for other-cause mortality. RESULTS: Of 1134 SFT patients, 87% underwent surgical resection. Most of the tumors were in the chest (28%), central nervous system (22%), head and neck (11%), pelvis (11%), extremities (10%), abdomen (10%) and retroperitoneum (6%), in that order. Stage was distributed as follows: localized (42%) vs. locally advanced (35%) vs. metastatic (13%). In multivariable competing risks models, independent predictors of higher CSM were stage (locally advanced HR: 1.6; metastatic HR: 2.9), non-surgical management (HR: 3.6) and tumor size (9-15.9 cm HR: 1.6; ≥16 cm HR: 1.9). CONCLUSIONS: We validated the importance of stage and surgical resection as independent predictors of CSM in malignant SFTs. Moreover, we provide novel observations regarding the independent importance of tumor size, regardless of the site of origin, stage and/or surgical resection status.

The Effect of Surgical Resection on Cancer-Specific Mortality in Pelvic Soft Tissue Sarcoma According to Histologic Subtype and Stage.

Background/Objectives: The impact of surgical resection versus non-resection on cancer-specific mortality (CSM) in soft tissue pelvic sarcoma remains largely unclear, particularly when considering histologic subtypes such as liposarcoma, leiomyosarcoma, and sarcoma NOS. The objective of the present study was to first report data regarding the association between surgical resection status and CSM in soft tissue pelvic sarcoma. Methods: Using data from the Surveillance, Epidemiology, and End Results (SEER) database from 2000 to 2019, we identified 2491 patients diagnosed with pelvic soft tissue sarcoma. Cumulative incidence plots were used to illustrate CSM and other-cause mortality rates based on the histologic subtype and surgical resection status. Competing risk regression models were employed to assess whether surgical resection was an independent predictor of CSM in both non-metastatic and metastatic patients. Results: Among the 2491 patients with soft tissue pelvic sarcoma, liposarcoma was the most common subtype (41%), followed by leiomyosarcoma (39%) and sarcoma NOS (20%). Surgical resection rates were 92% for liposarcoma, 91% for leiomyosarcoma, and 58% for sarcoma NOS in non-metastatic patients, while for metastatic patients, the rates were 55%, 49%, and 23%, respectively. In non-metastatic patients who underwent surgical resection, five-year CSM rates by histologic subtype were 10% for liposarcoma, 32% for leiomyosarcoma, and 27% for sarcoma NOS. The multivariable competing risk regression analysis showed that surgical resection provided a protective effect across all histologic subtypes in non-metastatic patients (liposarcoma HR: 0.2, leiomyosarcoma HR: 0.5, sarcoma NOS HR: 0.4). In metastatic patients, surgical resection had a protective effect for those with leiomyosarcoma (HR: 0.6) but not for those with sarcoma NOS. An analysis for metastatic liposarcoma was not possible due to insufficient data. Conclusions: In non-metastatic soft tissue pelvic sarcoma, surgical resection may be linked to a reduction in CSM. However, in metastatic patients, this protective effect appears to be limited primarily to those with leiomyosarcoma.

Image-Guided Stereotactic Body Radiotherapy on Detectable Prostate Bed Recurrence after Prostatectomy in RT-Naïve Patients.

Purpose or Objective-The aim of the study is to evaluate the efficacy and safety of SBRT on detectable prostate bed recurrence in RT-naïve prostate cancer patients. MATERIALS AND METHODS: Eighty-six patients who underwent SBRT for macroscopic bed recurrence after prostatectomy were retrospectively included. Patients were treated based on mpMRI or choline/PSMA PET. RESULTS: The median time to biochemical relapse (BCR) after RP was 46 months, with a median PSA at restaging of 1.04 ng/mL. Forty-six patients were staged with mpMRI and choline/PSMA PET, while ten and thirty were treated based on PET and MRI only, respectively. Only one late G ≥ 2 GI toxicity was observed. With a median BCR follow-up of 14 months, twenty-nine patients experienced a BCR with a median PSA at recurrence of 1.66 ng/mL and a median survival free from the event of 40.1 months. The median time to BCR was 17.9 months. Twenty-seven patients had clinical relapse (CR), with a median CR follow-up of 16.27 months and a median time to CR of 23.0 months. Biochemical recurrence-free survival at one and two years was 88% and 66%, respectively, while clinical recurrence-free survival at one and two years was 92% and 82%, respectively. Regarding local relapses, seven were in the field of treatment, while eight of them were outside the field of treatment. CONCLUSIONS: Data showed that SBRT targeting only the macroscopic bed recurrence instead of the whole prostate bed is safe and effective. Additional data and longer follow-ups will provide a clearer indication of the appropriate treatment and staging methodology for these patients.

Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models.

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.

Extreme-hypofractionated RT with concomitant boost to the DIL in PCa: a 5-year update on oncological and patient-reported outcomes for the phase II trial "GIVE ME FIVE".

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.

Time to progression is the main predictor of survival in patients with high-risk nonmuscle invasive bladder cancer: Results from a machine learning-based analysis of a large multi-institutional database.

BACKGROUND: In patients affected by high-risk nonmuscle invasive bladder cancer (HR-NMIBC) progression to muscle invasive status is considered as the main indicator of local treatment failure. We aimed to investigate the effect of progression and time to progression on overall survival (OS) and to investigate their validity as surrogate endpoints. METHODS: A total of 1,510 patients from 18 different institutions treated for T1 high grade NMIBC, followed by a secondary transurethral resection and BCG intravesical instillation. We relied on random survival forest (RSF) to rank covariates based on OS prediction. Cox's regression models were used to quantify the effect of covariates on mortality. RESULTS: During a median follow-up of 49.0 months, 485 (32.1%) patients progressed to MIBC, while 163 (10.8%) patients died. The median time to progression was 82 (95%CI: 78.0-93.0) months. In RSF time-to-progression and age were the most predictive covariates of OS. The survival tree defined 5 groups of risk. In multivariable Cox's regression models accounting for progression status as time-dependent covariate, shorter time to progression (as continuous covariate) was associated with longer OS (HR: 9.0, 95%CI: 3.0-6.7; P < 0.001). Virtually same results after time to progression stratification (time to progression ≥10.5 months as reference). CONCLUSION: Time to progression is the main predictor of OS in patients with high risk NMIBC treated with BCG and might be considered a coprimary endpoint. In addition, models including time to progression could be considered for patients' stratification in clinical practice and at the time of clinical trials design.

Advanced Age Impacts Survival After Radical Nephroureterectomy for Upper Tract Urothelial Carcinoma.

INTRODUCTION: Upper tract urothelial carcinoma is rare but has a poor prognosis. Prognostic factors have been extensively studied in order to provide the best possible management for patients. We have aimed to investigate commonly available factors predictive of recurrence and survival in this patient population at high risk of death and recurrence, with an emphasis on the effects of age (using a cutoff of 70 years) on survival outcomes. PATIENTS AND METHODS: From 1387 patients with clinically nonmetastatic upper tract urothelial carcinoma treated with radical nephroureterectomy at 21 academic hospital centers between 2005 and 2021, 776 patients were eligible and included in the study. Univariable and multivariable Cox regression models were built to evaluate the independent prognosticators for intravesical and extravesical recurrence, overall survival, and cancer-specific survival according to age groups. A P value of <.05 was considered statistically significant. RESULTS: We did not find an association between groups aged <70 and >70 years old and preoperatively clinical or histopathological characteristics. Kaplan-Meier analysis was found no statistical significance between the 2 age groups in terms of intravesical or extravesical recurrence (P = .09 and P = .57). Overall survival (P = .0001) and cancer-specific survival (P = .0001) have been found to be statistically significantly associated with age as independent predictors (confounding factors: gender, tumor size, tumor side, clinical T stage, localization, preoperative hydronephrosis, tumor localization, type of surgery, multifocality of the tumor, pathological grade, lymphovascular invasion, concomitant CIS, lymph node status, necrosis, or history of previous bladder cancer). CONCLUSION: This research confirms that patients aged 70 and above who undergo radical nephroureterectomy may have worse outcomes compared to younger patients, older patients needing an improved care and management of UTUC to improve their outcomes in the setting of an increase in this aged population group.

Investigating Nutritional and Inflammatory Status as Predictive Biomarkers in Oligoreccurent Prostate Cancer-A RADIOSA Trial Preliminary Analysis.

(1) Background: In the RADIOSA phase II randomized clinical trial (NCT03940235), the biology task entails the identification of predictive and prognostic biomarkers in the context of oligorecurrent, castration-sensitive prostate cancer in order to distinguish polymetastatic from oligometastatic disease. This may lay the groundwork for personalized treatments for those patients who could really benefit from metastasis-directed therapies. (2) Methods: Oligorecurrent PCa pts with three or fewer bone or lymph nodal localizations were randomized 1:1 to receive SBRT alone (arm A) or SBRT + 6 months of ADT (arm B). Common serum-derived biomarkers were collected at baseline, and at 3 months after RT. The prognostic nutritional index, an immune and nutrition-based prognostic score, and the controlling nutritional status (CONUT) score, a scoring system for evaluating patient's nutritional status, were calculated in accordance with the body of available literature. As inflammatory indicators, neutrophil-lymphocyte ratio (NLR) and the NLR-albumin ratio (NLRAR) were assessed. Changes in these parameters between baseline and the 3-month timepoint were evaluated both in absolute and relative values. Changes in these parameters between baseline and the 3-month timepoint were evaluated. Significant differences in the trend of these parameters were assessed using the non-parametric Wilcoxon rank-sum test. A network analysis to analyze the relationships between different features stratifying patients according to the arm of study and site of metastases was performed. (3) Results: The current analysis comprised 88 patients (45 arm A, SBRT only, and 43 arm B, SBRT + ADT). When patients were stratified by ADT administration, cholesterol values showed an increasing trend in the group receiving ADT (p = 0.005) which was no longer significant at 1 year. When patients were stratified by site of metastases (52 lymph nodal, 29 bone localizations), the value of NLR was found to be increased in patients with bone localizations (p < 0.05). In addition, the network analysis showed that BMI and NRI are strongly and directly linked for patients at baseline and that this correlation is no longer found at three months. Finally, when patients were divided according to time from surgery to oligorecurrence (enrollment) the patients with a longer time (>6.7 years) showed an increase in CONUT score from baseline. All the other nutritional and inflammatory scores or parameters investigated in the present analysis showed no statistically significant differences at baseline, three months, 1 year, and in absolute change. (4) Conclusions: The nutritional and inflammatory parameters do not seem to represent valuable candidates for possible use in clinical decision making in our cohort of patients and a reliable biological characterization of the oligometastatic state in prostate cancer still seems far from being achieved. Ongoing molecular analysis will show if there is a role of mutational landscape in the definition of the oligometastatic state.

Predicting Peri-Operative Outcomes in Patients Treated with Percutaneous Thermal Ablation for Small Renal Masses: The SuNS Nephrometry Score.

Our objective was to develop a new, simple, and ablation-specific nephrometry score to predict peri-operative outcomes and to compare its predictive accuracy to PADUA and RENAL scores. Overall, 418 patients were treated with percutaneous thermal ablation (microwave and radiofrequency) between 2008 and 2021. The outcome of interest was trifecta status (achieved vs. not achieved): incomplete ablation or Clavien-Dindo ≥ 3 complications or postoperative estimated glomerular filtration rate decrease ≥ 30%. First, we validated the discrimination ability of the PADUA and RENAL scoring systems. Second, we created and internally validated a novel scoring (SuNS) system, according to multivariable logistic regression models. The predictive accuracy of the model was tested in terms of discrimination and calibration. Overall, 89 (21%) patients did not achieve trifecta. PADUA and RENAL scores showed poor ability to predict trifecta status (c-indexes 0.60 [0.53-0.67] and 0.62 [0.55-0.69], respectively). We, therefore, developed the SuNS model (c-index: 0.74 [0.67-0.79]) based on: (1) contact surface area; (2) nearness to renal sinus or urinary collecting system; (3) tumour diameter. Three complexity classes were created: low (3-4 points; 11% of no trifecta) vs. moderate (5-6 points; 30% of no trifecta) vs. high (7-8 points; 65% of no trifecta) complexity. Limitations include the retrospective and single-institution nature of the study. In conclusion, we developed an immediate, simple, and reproducible ablation-specific nephrometry score (SuNS) that outperformed PADUA and RENAL nephrometry scores in predicting peri-operative outcomes. External validation is required before daily practice implementation.

Artificial Intelligence in the Advanced Diagnosis of Bladder Cancer-Comprehensive Literature Review and Future Advancement.

Artificial intelligence is highly regarded as the most promising future technology that will have a great impact on healthcare across all specialties. Its subsets, machine learning, deep learning, and artificial neural networks, are able to automatically learn from massive amounts of data and can improve the prediction algorithms to enhance their performance. This area is still under development, but the latest evidence shows great potential in the diagnosis, prognosis, and treatment of urological diseases, including bladder cancer, which are currently using old prediction tools and historical nomograms. This review focuses on highly significant and comprehensive literature evidence of artificial intelligence in the management of bladder cancer and investigates the near introduction in clinical practice.

What is the best time for postoperative radiation therapy in pN1 prostate cancer?

We retrospectively compared long-term biochemical recurrence rates (BCR) in pN1 PCa patients that underwent adjuvant radiotherapy (aRT) vs. no aRT/early salvage (esRT) after robot-assisted radical prostatectomy and extended pelvic lymphadenectomy. All PCa pN1 M0 patients treated at a single high-volume center between 2010 and 2020 were analyzed. Patients with <10 LNs yield, or >10 positive LNs, or persistently detectable PSA after RARP were excluded. Kaplan-Meier (KM) plots depicted BCR rates. Multivariable Cox regression models (MCRMs) focused on predictors of BCR. The cumulative incidence plot depicted BCR rates after propensity score (PS) matching (ratio 1:1). 220 pN1 patients were enrolled, 133 (60.4%) treated with aRT and 87 (39.6%) with no-aRT/esRT. aRT patients were older, with higher rates of postoperative ISUP grade group 4-5, and higher rates of pT3b stage. The actuarial BCR was similar (aRT 39.8% vs. no-aRT/esRT 40.2%; p=1). Median time to BCR was 62 vs. 38 months in aRT vs. no-aRT/esRT patients (p=0.001). In MCRMs, patients managed with no-aRT/esRT were associated with higher rates of BCR over time (hazard ratio [HR]: 3.27, p<0.001). ISUP grade group 5 (HR: 2.18, p<0.01) was an independent predictor of BCR. In PS-matched cumulative incidence plots, the BCR rate was significantly higher in the aRT group (76.4 vs. 40.4%; p<0.01). Patients managed with no-aRT/esRT experienced BCR approximately two years before the aRT group. Despite, the important BCR benefit after aRT, this treatment strategy is underused in daily practice.

Artificial intelligence and radiomics in evaluation of kidney lesions: a comprehensive literature review.

Radiomics and artificial intelligence (AI) may increase the differentiation of benign from malignant kidney lesions, differentiation of angiomyolipoma (AML) from renal cell carcinoma (RCC), differentiation of oncocytoma from RCC, differentiation of different subtypes of RCC, to predict Fuhrman grade, to predict gene mutation through molecular biomarkers and to predict treatment response in metastatic RCC undergoing immunotherapy. Neural networks analyze imaging data. Statistical, geometrical, textural features derived are giving quantitative data of contour, internal heterogeneity and gray zone features of lesions. A comprehensive literature review was performed, until July 2022. Studies investigating the diagnostic value of radiomics in differentiation of renal lesions, grade prediction, gene alterations, molecular biomarkers and ongoing clinical trials have been analyzed. The application of AI and radiomics could lead to improved sensitivity, specificity, accuracy in detecting and differentiating between renal lesions. Standardization of scanner protocols will improve preoperative differentiation between benign, low-risk cancers and clinically significant renal cancers and holds the premises to enhance the diagnostic ability of imaging tools to characterize renal lesions.

Critical Appraisal of Leibovich 2018 and GRANT Models for Prediction of Cancer-Specific Survival in Non-Metastatic Chromophobe Renal Cell Carcinoma.

Within the Surveillance, Epidemiology, and End Results database (2000-2019), we identified 5522 unilateral surgically treated non-metastatic chromophobe kidney cancer (chRCC) patients. This population was randomly divided into development vs. external validation cohorts. In the development cohort, the original Leibovich 2018 and GRANT categories were applied to predict 5- and 10-year cancer-specific survival (CSS). Subsequently, a novel multivariable nomogram was developed. Accuracy, calibration and decision curve analyses (DCA) tested the Cox regression-based nomogram as well as the Leibovich 2018 and GRANT risk categories in the external validation cohort. The accuracy of the Leibovich 2018 and GRANT models was 0.65 and 0.64 at ten years, respectively. The novel prognostic nomogram had an accuracy of 0.78 at ten years. All models exhibited good calibration. In DCA, Leibovich 2018 outperformed the novel nomogram within selected ranges of threshold probabilities at ten years. Conversely, the novel nomogram outperformed Leibovich 2018 for other values of threshold probabilities. In summary, Leibovich 2018 and GRANT risk categories exhibited borderline low accuracy in predicting CSS in North American non-metastatic chRCC patients. Conversely, the novel nomogram exhibited higher accuracy. However, in DCA, all examined models exhibited limitations within specific threshold probability intervals. In consequence, all three examined models provide individual predictions that might be suboptimal and be affected by limitations determined by the natural history of chRCC, where few deaths occur within ten years from surgery. Further investigations regarding established and novel predictors of CSS and relying on large sample sizes with longer follow-up are needed to better stratify CSS in chRCC.

Comparison of automated segmentation techniques for magnetic resonance images of the prostate.

BACKGROUND: Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs. METHODS: This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70/30 and one 50/50 train/test data split. We also analyzed the association between segmentation performance and clinical variables. RESULTS: The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables. CONCLUSIONS: Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855[Formula: see text]0.887 Dice).

Quality assurance for automatically generated contours with additional deep learning.

OBJECTIVE: Deploying an automatic segmentation model in practice should require rigorous quality assurance (QA) and continuous monitoring of the model's use and performance, particularly in high-stakes scenarios such as healthcare. Currently, however, tools to assist with QA for such models are not available to AI researchers. In this work, we build a deep learning model that estimates the quality of automatically generated contours. METHODS: The model was trained to predict the segmentation quality by outputting an estimate of the Dice similarity coefficient given an image contour pair as input. Our dataset contained 60 axial T2-weighted MRI images of prostates with ground truth segmentations along with 80 automatically generated segmentation masks. The model we used was a 3D version of the EfficientDet architecture with a custom regression head. For validation, we used a fivefold cross-validation. To counteract the limitation of the small dataset, we used an extensive data augmentation scheme capable of producing virtually infinite training samples from a single ground truth label mask. In addition, we compared the results against a baseline model that only uses clinical variables for its predictions. RESULTS: Our model achieved a mean absolute error of 0.020 ± 0.026 (2.2% mean percentage error) in estimating the Dice score, with a rank correlation of 0.42. Furthermore, the model managed to correctly identify incorrect segmentations (defined in terms of acceptable/unacceptable) 99.6% of the time. CONCLUSION: We believe that the trained model can be used alongside automatic segmentation tools to ensure quality and thus allow intervention to prevent undesired segmentation behavior.

Radiomics in prostate cancer: an up-to-date review.

Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.

Predictive clinico-pathological factors to identify BCG, unresponsive patients, after re-resection for T1 high grade non-muscle invasive bladder cancer.

INTRODUCTION: Seventy-five percent of bladder cancers are non-muscle invasive. The treatment strategy includes the transurethral resection of bladder tumor (TURB) followed by intravesical immunotherapy with the bacillus of Calmette-Guerin (BCG) or chemotherapy, depending on the grade of bladder tumor. Despite a proper BCG intravesical instillations schedule, up to 40% of patients present a failure within 2 years. The aim of this retrospective study was to investigate the predictive factors in the response to BCG in patients with a high-grade non-muscle invasive bladder cancer diagnosis. MATERIALS AND METHODS: Patients with non-muscle invasive bladder cancer from 13 hospitals and academic institutions were identified and treated, from January 1, 2002, until December 31, 2012, with TURB and a subsequent re-TURB for restaging before receiving BCG. Follow-up was performed with urine cytology and cystoscopy every 3 months for 1 year and, successively every 6 months. Univariate and multivariate Cox regression models addressed the response to BCG therapy. Kaplan-Meier overall survival (OS) and cancer-specific survival (CSS) estimates were determined for BCG responsive vs. BCG unresponsive patients. RESULTS: A total of 1,228 patients with non-muscle invasive bladder cancer were enrolled. Of 257 (20.9%) patients were BCG unresponsive. Independent predictive factors for response to BCG were: multifocality (HR: 1.4; 95% CI 1.05-1.86; P = 0.019), lymphovascular invasion (HR: 1.75; 95% CI 1.22-2.49; P = 0.002) and high-grade on re-TURB (HR: 1.39; 95% CI 1.02-1.91; P = 0.037). Overall survival was significantly reduced in BCG-unresponsive patients compared to BCG-responsive patients at 5 years (82.9% vs. 92.4%, P < 0.0001) and at 10 years (44.2% vs. 74.4%, P < 0.0001). Similarly, cancer-specific survival was reduced in BCG-unresponsive patients at 5 years (90.6% vs. 97.3%, P < 0.0001) and at 10 years (72.3% vs. 87.2%, P < 0.0001). CONCLUSION: Multifocality, lymphovascular invasion, and high-grade on re-TURB were independent predictors for response to BCG treatment. BCG-unresponsive patients reported worse oncological outcomes.

Modified Glasgow Prognostic Score as a Predictor of Recurrence in Patients with High Grade Non-Muscle Invasive Bladder Cancer Undergoing Intravesical Bacillus Calmette-Guerin Immunotherapy.

BACKGROUND: A systemic inflammatory marker, the modified Glasgow prognostic score (mGPS), could predict outcomes in non-muscle-invasive bladder cancer (NIMBC). We aimed to investigate the predictive power of mGPS in oncological outcomes in HG/G3 T1 NMIBC patients undergoing Bacillus Calmette-Guérin (BCG) therapy. METHODS: We retrospectively reviewed patient's medical data from multicenter institutions. A total of 1382 patients with HG/G3 T1 NMIBC have been administered adjuvant intravesical BCG therapy, every week for 3 weeks given at 3, 6, 12, 18, 24, 30 and 36 months. The analysis of mGPS for recurrence and progression was performed using multivariable and univariable Cox regression models. RESULTS: During follow-up, 659 patients (47.68%) suffered recurrence, 441 (31.91%) suffered progression, 156 (11.28%) died of all causes, and 67 (4.84%) died of bladder cancer. At multivariable analysis, neutrophil to lymphocyte ratio [hazard ratio (HR): 7.471; p = 0.0001] and erythrocyte sedimentation rate (ESR) (HR: 0.706; p = 0.006 were significantly associated with recurrence. mGPS has no statistical significance for progression (p = 0.076). Kaplan-Meier survival analysis showed a significant difference in survival among patients from different mGPS subgroups. Five-year OS was 93% (CI 95% 92-94), in patients with mGPS 0, 82.2% (CI 95% 78.9-85.5) in patients with mGPS 1 and 78.1% (CI 95% 60.4-70) in mGPS 2 patients. Five-year CSS was 98% (CI 95% 97-99) in patients with mGPS 0, 90% (CI 95% 87-94) in patients with mGPS 1, and 100% in mGPS 2 patients. Limitations are applicable to a retrospective study. CONCLUSIONS: mGPS may have the potential to predict recurrence in HG/G3 T1 NMIBC patients, but more prospective, with large cohorts, studies are needed to study the influence of systemic inflammatory markers in prediction of outcomes in NMIBC for a definitive conclusion.

Impact of Age on Outcomes of Patients With Pure Carcinoma In Situ of the Bladder: Multi-Institutional Cohort Analysis.

INTRODUCTION: The aim of this multicenter study was to investigate the role of age (cut-off 70 years) at diagnosis in predicting oncologic behavior of pure carcinoma in situ of the bladder. MATERIAL AND METHODS: Inclusion criteria were: patients with pure CIS confirmed and that followed intravesical BCG treatment. Pure CIS was defined at any CIS not associated with another urothelial cancer. Exclusion criteria were: any CIS associated with invasive urothelial carcinoma. A total of 172 with pure CIS treated between January 1, 2002 and December 31, 2012 at 8 academic institutions met the inclusion criteria. The maintenance schedule was generally according to the EAU guidelines at the time RESULTS: A total of 99 (57.6%) patients had an age >70 years prior to TURBT. There was no difference between clinico-pathologic features among groups (group 1, age ≤ 70 years and group 2, age > 70 years), except that patients aged ≤ 70 years presented a larger size of CIS (35.6% vs. 21.2%), P = .02. In multivariable Cox regression analyses, the same clinico-pathologic factors (age, multifocality, and recurrent tumor state) were independently associated with worse RFS. Harrell's C-index was 65.75.In multivariable Cox regression analyses in addition to age (P = .006) and multifocality (P < .001) also BMI (P = .04) was independently associated with worse PFS. Harrell's C-index was 74.71 CONCLUSION: Advanced age at diagnosis appears to be associated with an increased risk of recurrence and progression of pure carcinoma in situ of the bladder. Elderly patients might fail to respond to BCG therapy.

Correlation between radiological and biological features and clinical outcomes in early prostate cancer: an exploratory subgroup analysis.

PTEN deletion and Ki-67 expression are two of the most promising biomarkers in prostate cancer (PCa). In the same manner, multiparametric magnetic resonance imaging (mp-MRI) guided core biopsy is a powerful tool for PCa detection and staging. The aim of the study is to assess whether a correlation can be identified between the pathological stage defined by an mp-MRI-guided core biopsy and Ki-67 expression and PTEN deletion. Such correlation might be useful for staging and treatment personalization in PCa. This investigation was conducted in the context of phase II clinical study "Short-term radiotherapy for early prostate cancer with a concomitant boost to the dominant lesion" (AIRC IG-13218), ClinicalTrials.gov identifier: NCT01913717. Nineteen patients underwent a further in-bore MRI-targeted core biopsy (MRI-TBx) on the dominant intraprostatic lesion (DIL); on this basis, an additional Gleason Score (GS) was determined. PTEN loss and Ki-67 expression on these samples were analyzed and correlated with both risk categories modifications and oncological outcomes (overall survival, biochemical and clinical relapse). GS was upgraded in 5 cases, with 4 patients re-classified as intermediate-risk and 1 patient as high-risk. The latter experienced a clinical local relapse. No correlations between up/down-staging, PTEN deletion, and Ki-67 expression were observed in this cohort. Further investigations are needed towards the identification of a pattern in the tumor aggressiveness-response in PCa treated with ultra-hypofractionated radiotherapy. Moreover, a possible relationship between biomarker analysis and imaging textural features could be explored.